Marcel Worring

Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen et al. · nvidia

The goal of video summarization is to automatically shorten videos such that it conveys the overall story without losing relevant information. In many application scenarios, improper video summarization can have a large impact. For example in forensics, the quality of the generated video summary will affect an investigator's judgment while in journalism it might yield undesired bias. Because of this, modeling explainability is a key concern. One of the best ways to address the explainability challenge is to uncover the causal relations that steer the process and lead to the result. Current machine learning-based video summarization algorithms learn optimal parameters but do not uncover causal relationships. Hence, they suffer from a relative lack of explainability. In this work, a Causal Explainer, dubbed Causalainer, is proposed to address this issue. Multiple meaningful random variables and their joint distributions are introduced to characterize the behaviors of key components in the problem of video summarization. In addition, helper distributions are introduced to enhance the effectiveness of model training. In visual-textual input scenarios, the extra input can decrease the model performance. A causal semantics extractor is designed to tackle this issue by effectively distilling the mutual information from the visual and textual inputs. Experimental results on commonly used benchmarks demonstrate that the proposed method achieves state-of-the-art performance while being more explainable.

Tom van Sonsbeek, Mohammad Mahdi Derakhshani, Ivona Najdenkoska et al.

Medical Visual Question Answering (VQA) is an important challenge, as it would lead to faster and more accurate diagnoses and treatment decisions. Most existing methods approach it as a multi-class classification problem, which restricts the outcome to a predefined closed-set of curated answers. We focus on open-ended VQA and motivated by the recent advances in language models consider it as a generative task. Leveraging pre-trained language models, we introduce a novel method particularly suited for small, domain-specific, medical datasets. To properly communicate the medical images to the language model, we develop a network that maps the extracted visual features to a set of learnable tokens. Then, alongside the question, these learnable tokens directly prompt the language model. We explore recent parameter-efficient fine-tuning strategies for language models, which allow for resource- and data-efficient fine-tuning. We evaluate our approach on the prime medical VQA benchmarks, namely, Slake, OVQA and PathVQA. The results demonstrate that our approach outperforms existing methods across various training settings while also being computationally efficient.

Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen et al. · nvidia

Recently, video summarization has been proposed as a method to help video exploration. However, traditional video summarization models only generate a fixed video summary which is usually independent of user-specific needs and hence limits the effectiveness of video exploration. Multi-modal video summarization is one of the approaches utilized to address this issue. Multi-modal video summarization has a video input and a text-based query input. Hence, effective modeling of the interaction between a video input and text-based query is essential to multi-modal video summarization. In this work, a new causality-based method named Causal Video Summarizer (CVS) is proposed to effectively capture the interactive information between the video and query to tackle the task of multi-modal video summarization. The proposed method consists of a probabilistic encoder and a probabilistic decoder. Based on the evaluation of the existing multi-modal video summarization dataset, experimental results show that the proposed approach is effective with the increase of +5.4% in accuracy and +4.92% increase of F 1- score, compared with the state-of-the-art method.

Jia-Hong Huang, Chao-Han Huck Yang, Pin-Yu Chen et al. · nvidia

The aim of video summarization is to shorten videos automatically while retaining the key information necessary to convey the overall story. Video summarization methods mainly rely on visual factors, such as visual consecutiveness and diversity, which may not be sufficient to fully understand the content of the video. There are other non-visual factors, such as interestingness, representativeness, and storyline consistency that should also be considered for generating high-quality video summaries. Current methods do not adequately take into account these non-visual factors, resulting in suboptimal performance. In this work, a new approach to video summarization is proposed based on insights gained from how humans create ground truth video summaries. The method utilizes a conditional modeling perspective and introduces multiple meaningful random variables and joint distributions to characterize the key components of video summarization. Helper distributions are employed to improve the training of the model. A conditional attention module is designed to mitigate potential performance degradation in the presence of multi-modal input. The proposed video summarization method incorporates the above innovative design choices that aim to narrow the gap between human-generated and machine-generated video summaries. Extensive experiments show that the proposed approach outperforms existing methods and achieves state-of-the-art performance on commonly used video summarization datasets.

Mohammad Mahdi Derakhshani, Ivona Najdenkoska, Tom van Sonsbeek et al.

Deep learning models have shown a great effectiveness in recognition of findings in medical images. However, they cannot handle the ever-changing clinical environment, bringing newly annotated medical data from different sources. To exploit the incoming streams of data, these models would benefit largely from sequentially learning from new samples, without forgetting the previously obtained knowledge. In this paper we introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection, by applying existing state-of-the-art continual learning methods. In particular, we consider three continual learning scenarios, namely, task and class incremental learning and the newly defined cross-domain incremental learning. Task and class incremental learning of diseases address the issue of classifying new samples without re-training the models from scratch, while cross-domain incremental learning addresses the issue of dealing with datasets originating from different institutions while retaining the previously obtained knowledge. We perform a thorough analysis of the performance and examine how the well-known challenges of continual learning, such as the catastrophic forgetting exhibit themselves in this setting. The encouraging results demonstrate that continual learning has a major potential to advance disease classification and to produce a more robust and efficient learning framework for clinical settings. The code repository, data partitions and baseline results for the complete benchmark will be made publicly available.

Ivona Najdenkoska, Xiantong Zhen, Marcel Worring

Multimodal few-shot learning is challenging due to the large domain gap between vision and language modalities. Existing methods are trying to communicate visual concepts as prompts to frozen language models, but rely on hand-engineered task induction to reduce the hypothesis space. To make the whole process learnable, we introduce a multimodal meta-learning approach. Specifically, our approach decomposes the training of the model into a set of related multimodal few-shot tasks. We define a meta-mapper network, acting as a meta-learner, to efficiently bridge frozen large-scale vision and language models and leverage their already learned capacity. By updating the learnable parameters only of the meta-mapper, it learns to accrue shared meta-knowledge among these tasks. Thus, it can rapidly adapt to newly presented samples with only a few gradient updates. Importantly, it induces the task in a completely data-driven manner, with no need for a hand-engineered task induction. We evaluate our approach on recently proposed multimodal few-shot benchmarks, measuring how rapidly the model can bind novel visual concepts to words and answer visual questions by observing only a limited set of labeled examples. The experimental results show that our meta-learning approach outperforms the baseline across multiple datasets and various training settings while being computationally more efficient.

Jiayi Shen, Zehao Xiao, Xiantong Zhen et al.

In this paper, we focus on multi-task classification, where related classification tasks share the same label space and are learned simultaneously. In particular, we tackle a new setting, which is more realistic than currently addressed in the literature, where categories shift from training to test data. Hence, individual tasks do not contain complete training data for the categories in the test set. To generalize to such test data, it is crucial for individual tasks to leverage knowledge from related tasks. To this end, we propose learning an association graph to transfer knowledge among tasks for missing classes. We construct the association graph with nodes representing tasks, classes and instances, and encode the relationships among the nodes in the edges to guide their mutual knowledge transfer. By message passing on the association graph, our model enhances the categorical information of each instance, making it more discriminative. To avoid spurious correlations between task and class nodes in the graph, we introduce an assignment entropy maximization that encourages each class node to balance its edge weights. This enables all tasks to fully utilize the categorical information from related tasks. An extensive evaluation on three general benchmarks and a medical dataset for skin lesion classification reveals that our method consistently performs better than representative baselines.

Jia-Hong Huang, Modar Alfadly, Bernard Ghanem et al.

Deep neural networks have been critical in the task of Visual Question Answering (VQA), with research traditionally focused on improving model accuracy. Recently, however, there has been a trend towards evaluating the robustness of these models against adversarial attacks. This involves assessing the accuracy of VQA models under increasing levels of noise in the input, which can target either the image or the proposed query question, dubbed the main question. However, there is currently a lack of proper analysis of this aspect of VQA. This work proposes a new method that utilizes semantically related questions, referred to as basic questions, acting as noise to evaluate the robustness of VQA models. It is hypothesized that as the similarity of a basic question to the main question decreases, the level of noise increases. To generate a reasonable noise level for a given main question, a pool of basic questions is ranked based on their similarity to the main question, and this ranking problem is cast as a LASSO optimization problem. Additionally, this work proposes a novel robustness measure, R_score, and two basic question datasets to standardize the analysis of VQA model robustness. The experimental results demonstrate that the proposed evaluation method effectively analyzes the robustness of VQA models. Moreover, the experiments show that in-context learning with a chain of basic questions can enhance model accuracy.

Jiayi Shen, Xiantong Zhen, Qi et al. · tsinghua

This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information across tasks and meta-knowledge among episodes to effectively tackle each task with limited data. Existing meta-learning methods often fail to take advantage of crucial heterogeneous information in a single episode, while multi-task learning models neglect reusing experience from earlier episodes. To address the problem of insufficient data, we develop Heterogeneous Neural Processes (HNPs) for the episodic multi-task setup. Within the framework of hierarchical Bayes, HNPs effectively capitalize on prior experiences as meta-knowledge and capture task-relatedness among heterogeneous tasks, mitigating data-insufficiency. Meanwhile, transformer-structured inference modules are designed to enable efficient inferences toward meta-knowledge and task-relatedness. In this way, HNPs can learn more powerful functional priors for adapting to novel heterogeneous tasks in each meta-test episode. Experimental results show the superior performance of the proposed HNPs over typical baselines, and ablation studies verify the effectiveness of the designed inference modules.

Jia-Hong Huang, Luka Murn, Marta Mrak et al.

Existing datasets for manually labelled query-based video summarization are costly and thus small, limiting the performance of supervised deep video summarization models. Self-supervision can address the data sparsity challenge by using a pretext task and defining a method to acquire extra data with pseudo labels to pre-train a supervised deep model. In this work, we introduce segment-level pseudo labels from input videos to properly model both the relationship between a pretext task and a target task, and the implicit relationship between the pseudo label and the human-defined label. The pseudo labels are generated based on existing human-defined frame-level labels. To create more accurate query-dependent video summaries, a semantics booster is proposed to generate context-aware query representations. Furthermore, we propose mutual attention to help capture the interactive information between visual and textual modalities. Three commonly-used video summarization benchmarks are used to thoroughly validate the proposed approach. Experimental results show that the proposed video summarization algorithm achieves state-of-the-art performance.

Tom van Sonsbeek, Xiantong Zhen, Dwarikanath Mahapatra et al.

Medical image datasets and their annotations are not growing as fast as their equivalents in the general domain. This makes translation from the newest, more data-intensive methods that have made a large impact on the vision field increasingly more difficult and less efficient. In this paper, we propose a new probabilistic latent variable model for disease classification in chest X-ray images. Specifically we consider chest X-ray datasets that contain global disease labels, and for a smaller subset contain object level expert annotations in the form of eye gaze patterns and disease bounding boxes. We propose a two-stage optimization algorithm which is able to handle these different label granularities through a single training pipeline in a two-stage manner. In our pipeline global dataset features are learned in the lower level layers of the model. The specific details and nuances in the fine-grained expert object-level annotations are learned in the final layers of the model using a knowledge distillation method inspired by conditional variational inference. Subsequently, model weights are frozen to guide this learning process and prevent overfitting on the smaller richly annotated data subsets. The proposed method yields consistent classification improvement across different backbones on the common benchmark datasets Chest X-ray14 and MIMIC-CXR. This shows how two-stage learning of labels from coarse to fine-grained, in particular with object level annotations, is an effective method for more optimal annotation usage.

Inske Groenen, Stevan Rudinac, Marcel Worring

Large collections of geo-referenced panoramic images are freely available for cities across the globe, as well as detailed maps with location and meta-data on a great variety of urban objects. They provide a potentially rich source of information on urban objects, but manual annotation for object detection is costly, laborious and difficult. Can we utilize such multimedia sources to automatically annotate street level images as an inexpensive alternative to manual labeling? With the PanorAMS framework we introduce a method to automatically generate bounding box annotations for panoramic images based on urban context information. Following this method, we acquire large-scale, albeit noisy, annotations for an urban dataset solely from open data sources in a fast and automatic manner. The dataset covers the City of Amsterdam and includes over 14 million noisy bounding box annotations of 22 object categories present in 771,299 panoramic images. For many objects further fine-grained information is available, obtained from geospatial meta-data, such as building value, function and average surface area. Such information would have been difficult, if not impossible, to acquire via manual labeling based on the image alone. For detailed evaluation, we introduce an efficient crowdsourcing protocol for bounding box annotations in panoramic images, which we deploy to acquire 147,075 ground-truth object annotations for a subset of 7,348 images, the PanorAMS-clean dataset. For our PanorAMS-noisy dataset, we provide an extensive analysis of the noise and how different types of noise affect image classification and object detection performance. We make both datasets, PanorAMS-noisy and PanorAMS-clean, benchmarks and tools presented in this paper openly available.

Mohammad Mahdi Derakhshani, Ivona Najdenkoska, Cees G. M. Snoek et al.

We present Self-Context Adaptation (SeCAt), a self-supervised approach that unlocks few-shot abilities for open-ended classification with small visual language models. Our approach imitates image captions in a self-supervised way based on clustering a large pool of images followed by assigning semantically-unrelated names to clusters. By doing so, we construct a training signal consisting of interleaved sequences of image and pseudocaption pairs and a query image, which we denote as the 'self-context' sequence. Based on this signal the model is trained to produce the right pseudo-caption. We demonstrate the performance and flexibility of SeCAt on several multimodal few-shot datasets, spanning various granularities. By using models with approximately 1B parameters we outperform the few-shot abilities of much larger models, such as Frozen and FROMAGe. SeCAt opens new possibilities for research and applications in open-ended few-shot learning that otherwise requires access to large or proprietary models.

Maarten Sukel, Stevan Rudinac, Marcel Worring

Multimodal demand forecasting aims at predicting product demand utilizing visual, textual, and contextual information. This paper proposes a method for multimodal product demand forecasting using convolutional, graph-based, and transformer-based architectures. Traditional approaches to demand forecasting rely on historical demand, product categories, and additional contextual information such as seasonality and events. However, these approaches have several shortcomings, such as the cold start problem making it difficult to predict product demand until sufficient historical data is available for a particular product, and their inability to properly deal with category dynamics. By incorporating multimodal information, such as product images and textual descriptions, our architecture aims to address the shortcomings of traditional approaches and outperform them. The experiments conducted on a large real-world dataset show that the proposed approach effectively predicts demand for a wide range of products. The multimodal pipeline presented in this work enhances the accuracy and reliability of the predictions, demonstrating the potential of leveraging multimodal information in product demand forecasting.

Nanne van Noord, Melvin Wevers, Tobias Blanke et al.

There is a bidirectional relationship between culture and AI; AI models are increasingly used to analyse culture, thereby shaping our understanding of culture. On the other hand, the models are trained on collections of cultural artifacts thereby implicitly, and not always correctly, encoding expressions of culture. This creates a tension that both limits the use of AI for analysing culture and leads to problems in AI with respect to cultural complex issues such as bias. One approach to overcome this tension is to more extensively take into account the intricacies and complexities of culture. We structure our discussion using four concepts that guide humanistic inquiry into culture: subjectivity, scalability, contextuality, and temporality. We focus on these concepts because they have not yet been sufficiently represented in AI research. We believe that possible implementations of these aspects into AI research leads to AI that better captures the complexities of culture. In what follows, we briefly describe these four concepts and their absence in AI research. For each concept, we define possible research challenges.

Merel de Leeuw den Bouter, Javier Lloret Pardo, Zeno Geradts et al.

In high-stakes settings, Machine Learning models that can provide predictions that are interpretable for humans are crucial. This is even more true with the advent of complex deep learning based models with a huge number of tunable parameters. Recently, prototype-based methods have emerged as a promising approach to make deep learning interpretable. We particularly focus on the analysis of deepfake videos in a forensics context. Although prototype-based methods have been introduced for the detection of deepfake videos, their use in real-world scenarios still presents major challenges, in that prototypes tend to be overly similar and interpretability varies between prototypes. This paper proposes a Visual Analytics process model for prototype learning, and, based on this, presents ProtoExplorer, a Visual Analytics system for the exploration and refinement of prototype-based deepfake detection models. ProtoExplorer offers tools for visualizing and temporally filtering prototype-based predictions when working with video data. It disentangles the complexity of working with spatio-temporal prototypes, facilitating their visualization. It further enables the refinement of models by interactively deleting and replacing prototypes with the aim to achieve more interpretable and less biased predictions while preserving detection accuracy. The system was designed with forensic experts and evaluated in a number of rounds based on both open-ended think aloud evaluation and interviews. These sessions have confirmed the strength of our prototype based exploration of deepfake videos while they provided the feedback needed to continuously improve the system.

Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic et al.

Sequential multiple-instance learning involves learning representations of sets distributed across discrete timesteps. In many real-world applications, modeling both the internal structure of sets and their temporal relationships across time is essential for capturing complex underlying patterns. However, existing methods either focus on learning set representations at a static level, ignoring temporal dynamics, or treat sequences as ordered lists of individual elements, lacking explicit mechanisms to represent sets. In this work, we propose Set2Seq Transformer, a novel architecture that jointly models permutation-invariant set structure and temporal dependencies by learning temporal and positional-aware representations of sets within a sequence in an end-to-end multimodal manner. We evaluate our Set2Seq Transformer on two tasks that require modeling both set structure alongside temporal and positional patterns, but differ significantly in domain, modality, and objective. First, we consider a fine-art analysis task, modeling artists' oeuvres for predicting artistic success using a novel dataset, WikiArt-Seq2Rank. Second, we utilize our Set2Seq Transformer for a short-term wildfire danger forecasting task. Through extensive experimentation, we show that our Set2Seq Transformer significantly improves over traditional static multiple-instance learning methods by effectively learning permutation-invariant set, temporal, and positional-aware representations across diverse domains, modalities, and tasks. We will release both the dataset and model implementations on GitHub.

Tom van Sonsbeek, Marcel Worring

An important component of human analysis of medical images and their context is the ability to relate newly seen things to related instances in our memory. In this paper we mimic this ability by using multi-modal retrieval augmentation and apply it to several tasks in chest X-ray analysis. By retrieving similar images and/or radiology reports we expand and regularize the case at hand with additional knowledge, while maintaining factual knowledge consistency. The method consists of two components. First, vision and language modalities are aligned using a pre-trained CLIP model. To enforce that the retrieval focus will be on detailed disease-related content instead of global visual appearance it is fine-tuned using disease class information. Subsequently, we construct a non-parametric retrieval index, which reaches state-of-the-art retrieval levels. We use this index in our downstream tasks to augment image representations through multi-head attention for disease classification and report retrieval. We show that retrieval augmentation gives considerable improvements on these tasks. Our downstream report retrieval even shows to be competitive with dedicated report generation methods, paving the path for this method in medical imaging.

Ujjwal Sharma, Stevan Rudinac, Ana Mićković et al.

In this work, we introduce a multimodal analysis pipeline that leverages large foundation models in vision and language to analyze corporate social media content, with a focus on sustainability-related communication. Addressing the challenges of evolving, multimodal, and often ambiguous corporate messaging on platforms such as X (formerly Twitter), we employ an ensemble of large language models (LLMs) to annotate a large corpus of corporate tweets on their topical alignment with the 17 Sustainable Development Goals (SDGs). This approach avoids the need for costly, task-specific annotations and explores the potential of such models as ad-hoc annotators for social media data that can efficiently capture both explicit and implicit references to sustainability themes in a scalable manner. Complementing this textual analysis, we utilize vision-language models (VLMs), within a visual understanding framework that uses semantic clusters to uncover patterns in visual sustainability communication. This integrated approach reveals sectoral differences in SDG engagement, temporal trends, and associations between corporate messaging, environmental, social, governance (ESG) risks, and consumer engagement. Our methods-automatic label generation and semantic visual clustering-are broadly applicable to other domains and offer a flexible framework for large-scale social media analysis.

Shuai Wang, Jiayi Shen, Athanasios Efthymiou et al.

The variety and complexity of relations in multimedia data lead to Heterogeneous Information Networks (HINs). Capturing the semantics from such networks requires approaches capable of utilizing the full richness of the HINs. Existing methods for modeling HINs employ techniques originally designed for graph neural networks, and HINs decomposition analysis, like using manually predefined metapaths. In this paper, we introduce a novel prototype-enhanced hypergraph learning approach for node classification in HINs. Using hypergraphs instead of graphs, our method captures higher-order relationships among nodes and extracts semantic information without relying on metapaths. Our method leverages the power of prototypes to improve the robustness of the hypergraph learning process and creates the potential to provide human-interpretable insights into the underlying network structure. Extensive experiments on three real-world HINs demonstrate the effectiveness of our method.

Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic et al.

Real-world multimodal knowledge graphs (MKGs) are inherently heterogeneous, modeling entities that are associated with diverse modalities. Traditional knowledge graph embedding (KGE) methods excel at learning continuous representations of entities and relations, yet they are typically designed for unimodal settings. Recent approaches extend KGE to multimodal settings but remain constrained, often processing modalities in isolation, resulting in weak cross-modal alignment, and relying on simplistic assumptions such as uniform modality availability across entities. Vision-Language Models (VLMs) offer a powerful way to align diverse modalities within a shared embedding space. We propose Vision-Language Knowledge Graph Embeddings (VL-KGE), a framework that integrates cross-modal alignment from VLMs with structured relational modeling to learn unified multimodal representations of knowledge graphs. Experiments on WN9-IMG and two novel fine art MKGs, WikiArt-MKG-v1 and WikiArt-MKG-v2, demonstrate that VL-KGE consistently improves over traditional unimodal and multimodal KGE methods in link prediction tasks. Our results highlight the value of VLMs for multimodal KGE, enabling more robust and structured reasoning over large-scale heterogeneous knowledge graphs.

Conor McCarthy, Jan Peter van Zandwijk, Marcel Worring et al.

Smartphones and smartwatches are ever-present in daily life, and provide a rich source of information on their users' behaviour. In particular, digital traces derived from the phone's embedded movement sensors present an opportunity for a forensic investigator to gain insight into a person's physical activities. In this work, we present a machine learning-based approach to translate digital traces into likelihood ratios (LRs) for different types of physical activities. Evaluating on a new dataset, NFI\_FARED, which contains digital traces from four different types of iPhones labelled with 19 activities, it was found that our approach could produce useful LR systems to distinguish 167 out of a possible 171 activity pairings. The same approach was extended to analyse likelihoods for multiple activities (or groups of activities) simultaneously and create activity timelines to aid in both the early and latter stages of forensic investigations. The dataset and all code required to replicate the results have also been made public to encourage further research on this topic.

Ivona Najdenkoska, Mohammad Mahdi Derakhshani, Yuki M. Asano et al.

We address the challenge of representing long captions in vision-language models, such as CLIP. By design these models are limited by fixed, absolute positional encodings, restricting inputs to a maximum of 77 tokens and hindering performance on tasks requiring longer descriptions. Although recent work has attempted to overcome this limit, their proposed approaches struggle to model token relationships over longer distances and simply extend to a fixed new token length. Instead, we propose a generalizable method, named TULIP, able to upgrade the token length to any length for CLIP-like models. We do so by improving the architecture with relative position encodings, followed by a training procedure that (i) distills the original CLIP text encoder into an encoder with relative position encodings and (ii) enhances the model for aligning longer captions with images. By effectively encoding captions longer than the default 77 tokens, our model outperforms baselines on cross-modal tasks such as retrieval and text-to-image generation. The code repository is available at https://github.com/ivonajdenkoska/tulip.

Shuai Wang, Hongyi Zhu, Jia-Hong Huang et al.

Understanding artworks requires multi-step reasoning over visual content and cultural, historical, and stylistic context. While recent multimodal large language models show promise in artwork explanation, they rely on implicit reasoning and internalized knowl- edge, limiting interpretability and explicit evidence grounding. We propose A-MAR, an Agent-based Multimodal Art Retrieval framework that explicitly conditions retrieval on structured reasoning plans. Given an artwork and a user query, A-MAR first decomposes the task into a structured reasoning plan that specifies the goals and evidence requirements for each step. Retrieval is then conditionedon this plan, enabling targeted evidence selection and supporting step-wise, grounded explanations. To evaluate agent-based multi- modal reasoning within the art domain, we introduce ArtCoT-QA. This diagnostic benchmark features multi-step reasoning chains for diverse art-related queries, enabling a granular analysis that extends beyond simple final answer accuracy. Experiments on SemArt and Artpedia show that A-MAR consistently outperforms static, non planned retrieval and strong MLLM baselines in final explanation quality, while evaluations on ArtCoT-QA further demonstrate its advantages in evidence grounding and multi-step reasoning ability. These results highlight the importance of reasoning-conditioned retrieval for knowledge-intensive multimodal understanding and position A-MAR as a step toward interpretable, goal-driven AI systems, with particular relevance to cultural industries. The code and data are available at: https://github.com/ShuaiWang97/A-MAR.

Yijia Zheng, Marcel Worring

Hypergraphs are widely being employed to represent complex higher-order relations in real-world applications. Most existing research on hypergraph learning focuses on node-level or edge-level tasks. A practically relevant and more challenging task, edge-dependent node classification (ENC), is still under-explored. In ENC, a node can have different labels across different hyperedges, which requires the modeling of node features unique to each hyperedge. The state-of-the-art ENC solution, WHATsNet, only outputs single node and edge representations, leading to the limitations of \textbf{entangled edge-specific features} and \textbf{non-adaptive representation sizes} when applied to ENC. Additionally, WHATsNet suffers from the common \textbf{oversmoothing issue} in most HGNNs. To address these limitations, we propose \textbf{CoNHD}, a novel HGNN architecture specifically designed to model edge-specific features for ENC. Instead of learning separate representations for nodes and edges, CoNHD reformulates within-edge and within-node interactions as a hypergraph diffusion process over node-edge co-representations. We develop a neural implementation of the proposed diffusion process, leveraging equivariant networks as diffusion operators to effectively learn the diffusion dynamics from data. Extensive experiments demonstrate that CoNHD achieves the best performance across all benchmark ENC datasets and several downstream tasks without sacrificing efficiency. Our implementation is available at https://github.com/zhengyijia/CoNHD.

Ana Vasilcoiu, Ivona Najdenkoska, Zeno Geradts et al.

The rapid advancement of diffusion-based image generators has made it increasingly difficult to distinguish generated from real images. This erodes trust in digital media, making it critical to develop generated image detectors that remain reliable across different generators. While recent approaches leverage diffusion denoising cues, they typically rely on single-step reconstruction errors and overlook the sequential nature of the denoising process. In this work, we propose LATTE - LATent Trajectory Embedding - a novel approach that models the evolution of latent embeddings across multiple denoising steps. Instead of treating each denoising step in isolation, LATTE captures the trajectory of these representations, revealing subtle and discriminative patterns that distinguish real from generated images. Experiments on several benchmarks, such as GenImage, Chameleon, and Diffusion Forensics, show that LATTE achieves superior performance, especially in challenging cross-generator and cross-dataset scenarios, highlighting the potential of latent trajectory modeling. The code is available on the following link: https://github.com/AnaMVasilcoiu/LATTE-Diffusion-Detector.

Mengran Li, Pengyu Zhang, Wenbin Xing et al.

Graphs are a widely used paradigm for representing non-Euclidean data, with applications ranging from social network analysis to biomolecular prediction. While graph learning has achieved remarkable progress, real-world graph data presents a number of challenges that significantly hinder the learning process. In this survey, we focus on four fundamental data-centric challenges: (1) Incompleteness, real-world graphs have missing nodes, edges, or attributes; (2) Imbalance, the distribution of the labels of nodes or edges and their structures for real-world graphs are highly skewed; (3) Cross-domain Heterogeneity, graphs from different domains exhibit incompatible feature spaces or structural patterns; and (4) Dynamic Instability, graphs evolve over time in unpredictable ways. Recently, Large Language Models (LLMs) offer the potential to tackle these challenges by leveraging rich semantic reasoning and external knowledge. This survey focuses on how LLMs can address four fundamental data-centric challenges in graph-structured data, thereby improving the effectiveness of graph learning. For each challenge, we review both traditional solutions and modern LLM-driven approaches, highlighting how LLMs contribute unique advantages. Finally, we discuss open research questions and promising future directions in this emerging interdisciplinary field. To support further exploration, we have curated a repository of recent advances on graph learning challenges: https://github.com/limengran98/Awesome-Literature-Graph-Learning-Challenges.

Sarah Ibrahimi, Nanne van Noord, Tim Alpherts et al.

Visual Place Recognition (VPR) is generally concerned with localizing outdoor images. However, localizing indoor scenes that contain part of an outdoor scene can be of large value for a wide range of applications. In this paper, we introduce Inside Out Visual Place Recognition (IOVPR), a task aiming to localize images based on outdoor scenes visible through windows. For this task we present the new large-scale dataset Amsterdam-XXXL, with images taken in Amsterdam, that consists of 6.4 million panoramic street-view images and 1000 user-generated indoor queries. Additionally, we introduce a new training protocol Inside Out Data Augmentation to adapt Visual Place Recognition methods for localizing indoor images, demonstrating the potential of Inside Out Visual Place Recognition. We empirically show the benefits of our proposed data augmentation scheme on a smaller scale, whilst demonstrating the difficulty of this large-scale dataset for existing methods. With this new task we aim to encourage development of methods for IOVPR. The dataset and code are available for research purposes at https://github.com/saibr/IOVPR

Jia-Hong Huang, Marcel Worring

When video collections become huge, how to explore both within and across videos efficiently is challenging. Video summarization is one of the ways to tackle this issue. Traditional summarization approaches limit the effectiveness of video exploration because they only generate one fixed video summary for a given input video independent of the information need of the user. In this work, we introduce a method which takes a text-based query as input and generates a video summary corresponding to it. We do so by modeling video summarization as a supervised learning problem and propose an end-to-end deep learning based method for query-controllable video summarization to generate a query-dependent video summary. Our proposed method consists of a video summary controller, video summary generator, and video summary output module. To foster the research of query-controllable video summarization and conduct our experiments, we introduce a dataset that contains frame-based relevance score labels. Based on our experimental result, it shows that the text-based query helps control the video summary. It also shows the text-based query improves our model performance. Our code and dataset: https://github.com/Jhhuangkay/Query-controllable-Video-Summarization.

Yijia Zheng, Marcel Worring

Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks but struggles with complex questions. Agentic RAG extends this paradigm by replacing single-step retrieval with a multi-step process, in which the large language model (LLM) acts as a search agent that generates intermediate thoughts and subqueries to iteratively interact with the retrieval system. This iterative process incurs substantial latency due to the autoregressive generation of lengthy thoughts and subqueries. To address this limitation, we propose LatentRAG, a novel framework that shifts both reasoning and retrieval from discrete language space to continuous latent space. Unlike existing explicit methods that generate natural language thoughts or subqueries token-by-token, LatentRAG produces latent tokens for thoughts and subqueries directly from the hidden states in a single forward pass. We align LLMs with dense retrieval models in the latent space, enabling retrieval over latent subquery tokens and supporting end-to-end joint optimization. To improve transparency and encourage semantically meaningful latent representations, we incorporate a parallel latent decoding mechanism that translates latent tokens back into natural language. Extensive experiments on seven benchmark datasets show that LatentRAG achieves performance comparable to explicit agentic RAG methods while reducing inference latency by approximately 90%, substantially narrowing the latency gap with traditional single-step RAG.

Jiayi Shen, Cheems Wang, Zehao Xiao et al. · tsinghua

This paper proposes \textit{GO4Align}, a multi-task optimization approach that tackles task imbalance by explicitly aligning the optimization across tasks. To achieve this, we design an adaptive group risk minimization strategy, comprising two techniques in implementation: (i) dynamical group assignment, which clusters similar tasks based on task interactions; (ii) risk-guided group indicators, which exploit consistent task correlations with risk information from previous iterations. Comprehensive experimental results on diverse benchmarks demonstrate our method's performance superiority with even lower computational costs.

Shuai Wang, Ivona Najdenkoska, Hongyi Zhu et al.

Understanding visual art requires reasoning across multiple perspectives -- cultural, historical, and stylistic -- beyond mere object recognition. While recent multimodal large language models (MLLMs) perform well on general image captioning, they often fail to capture the nuanced interpretations that fine art demands. We propose ArtRAG, a novel, training-free framework that combines structured knowledge with retrieval-augmented generation (RAG) for multi-perspective artwork explanation. ArtRAG automatically constructs an Art Context Knowledge Graph (ACKG) from domain-specific textual sources, organizing entities such as artists, movements, themes, and historical events into a rich, interpretable graph. At inference time, a multi-granular structured retriever selects semantically and topologically relevant subgraphs to guide generation. This enables MLLMs to produce contextually grounded, culturally informed art descriptions. Experiments on the SemArt and Artpedia datasets show that ArtRAG outperforms several heavily trained baselines. Human evaluations further confirm that ArtRAG generates coherent, insightful, and culturally enriched interpretations.

Marcel Worring, Jan Zahálka, Stef van den Elzen et al.

The rapid advances in Foundation Models and agentic Artificial Intelligence are transforming multimedia analytics by enabling richer, more sophisticated interactions between humans and analytical systems. Existing conceptual models for visual and multimedia analytics, however, do not adequately capture the complexity introduced by these powerful AI paradigms. To bridge this gap, we propose a comprehensive multimedia analytics model specifically designed for the foundation model era. Building upon established frameworks from visual analytics, multimedia analytics, knowledge generation, analytic task definition, mixed-initiative guidance, and human-in-the-loop reinforcement learning, our model emphasizes integrated human-AI teaming based on visual analytics agents from both technical and conceptual perspectives. Central to the model is a seamless, yet explicitly separable, interaction channel between expert users and semi-autonomous analytical processes, ensuring continuous alignment between user intent and AI behavior. The model addresses practical challenges in sensitive domains such as intelligence analysis, investigative journalism, and other fields handling complex, high-stakes data. We illustrate through detailed case studies how our model facilitates deeper understanding and targeted improvement of multimedia analytics solutions. By explicitly capturing how expert users can optimally interact with and guide AI-powered multimedia analytics systems, our conceptual framework sets a clear direction for system design, comparison, and future research.

Shuai Wang, David W. Zhang, Jia-Hong Huang et al.

Hypergraphs serve as an effective model for depicting complex connections in various real-world scenarios, from social to biological networks. The development of Hypergraph Neural Networks (HGNNs) has emerged as a valuable method to manage the intricate associations in data, though scalability is a notable challenge due to memory limitations. In this study, we introduce a new adaptive sampling strategy specifically designed for hypergraphs, which tackles their unique complexities in an efficient manner. We also present a Random Hyperedge Augmentation (RHA) technique and an additional Multilayer Perceptron (MLP) module to improve the robustness and generalization capabilities of our approach. Thorough experiments with real-world datasets have proven the effectiveness of our method, markedly reducing computational and memory demands while maintaining performance levels akin to conventional HGNNs and other baseline models. This research paves the way for improving both the scalability and efficacy of HGNNs in extensive applications. We will also make our codebase publicly accessible.

Conor McCarthy, Loes Quirijnen, Jan Peter van Zandwijk et al.

Within Human Activity Recognition (HAR), there is an insurmountable gap between the range of activities performed in life and those that can be captured in an annotated sensor dataset used in training. Failure to properly handle unseen activities seriously undermines any HAR classifier's reliability. Additionally within HAR, not all classes are equally dissimilar, some significantly overlap or encompass other sub-activities. Based on these observations, we arrange activity classes into a structured hierarchy. From there, we propose Hi-OSCAR: a Hierarchical Open-set Classifier for Activity Recognition, that can identify known activities at state-of-the-art accuracy while simultaneously rejecting unknown activities. This not only enables open-set classification, but also allows for unknown classes to be localized to the nearest internal node, providing insight beyond a binary "known/unknown" classification. To facilitate this and future open-set HAR research, we collected a new dataset: NFI_FARED. NFI_FARED contains data from multiple subjects performing nineteen activities from a range of contexts, including daily living, commuting, and rapid movements, which is fully public and available for download.

Yahia Dalbah, Marcel Worring, Yen-Chia Hsu

Urban air pollution is a major health crisis causing millions of premature deaths annually, underscoring the urgent need for accurate and scalable monitoring of air quality (AQ). While low-cost sensors (LCS) offer a scalable alternative to expensive reference-grade stations, their readings are affected by drift, calibration errors, and environmental interference. To address these challenges, we introduce Veli (Reference-free Variational Estimation via Latent Inference), an unsupervised Bayesian model that leverages variational inference to correct LCS readings without requiring co-location with reference stations, eliminating a major deployment barrier. Specifically, Veli constructs a disentangled representation of the LCS readings, effectively separating the true pollutant reading from the sensor noise. To build our model and address the lack of standardized benchmarks in AQ monitoring, we also introduce the Air Quality Sensor Data Repository (AQ-SDR). AQ-SDR is the largest AQ sensor benchmark to date, with readings from 23,737 LCS and reference stations across multiple regions. Veli demonstrates strong generalization across both in-distribution and out-of-distribution settings, effectively handling sensor drift and erratic sensor behavior. Code for model and dataset will be made public when this paper is published.

Tom van Sonsbeek, Xiantong Zhen, Marcel Worring

The way we analyse clinical texts has undergone major changes over the last years. The introduction of language models such as BERT led to adaptations for the (bio)medical domain like PubMedBERT and ClinicalBERT. These models rely on large databases of archived medical documents. While performing well in terms of accuracy, both the lack of interpretability and limitations to transfer across languages limit their use in clinical setting. We introduce a novel light-weight graph-based embedding method specifically catering radiology reports. It takes into account the structure and composition of the report, while also connecting medical terms in the report through the multi-lingual SNOMED Clinical Terms knowledge base. The resulting graph embedding uncovers the underlying relationships among clinical terms, achieving a representation that is better understandable for clinicians and clinically more accurate, without reliance on large pre-training datasets. We show the use of this embedding on two tasks namely disease classification of X-ray reports and image classification. For disease classification our model is competitive with its BERT-based counterparts, while being magnitudes smaller in size and training data requirements. For image classification, we show the effectiveness of the graph embedding leveraging cross-modal knowledge transfer and show how this method is usable across different languages.

Jiayi Shen, Xiantong Zhen, Marcel Worring et al.

Neural processes have recently emerged as a class of powerful neural latent variable models that combine the strengths of neural networks and stochastic processes. As they can encode contextual data in the network's function space, they offer a new way to model task relatedness in multi-task learning. To study its potential, we develop multi-task neural processes, a new variant of neural processes for multi-task learning. In particular, we propose to explore transferable knowledge from related tasks in the function space to provide inductive bias for improving each individual task. To do so, we derive the function priors in a hierarchical Bayesian inference framework, which enables each task to incorporate the shared knowledge provided by related tasks into its context of the prediction function. Our multi-task neural processes methodologically expand the scope of vanilla neural processes and provide a new way of exploring task relatedness in function spaces for multi-task learning. The proposed multi-task neural processes are capable of learning multiple tasks with limited labeled data and in the presence of domain shift. We perform extensive experimental evaluations on several benchmarks for the multi-task regression and classification tasks. The results demonstrate the effectiveness of multi-task neural processes in transferring useful knowledge among tasks for multi-task learning and superior performance in multi-task classification and brain image segmentation.

Jiayi Shen, Xiantong Zhen, Marcel Worring et al.

Multi-task learning aims to explore task relatedness to improve individual tasks, which is of particular significance in the challenging scenario that only limited data is available for each task. To tackle this challenge, we propose variational multi-task learning (VMTL), a general probabilistic inference framework for learning multiple related tasks. We cast multi-task learning as a variational Bayesian inference problem, in which task relatedness is explored in a unified manner by specifying priors. To incorporate shared knowledge into each task, we design the prior of a task to be a learnable mixture of the variational posteriors of other related tasks, which is learned by the Gumbel-Softmax technique. In contrast to previous methods, our VMTL can exploit task relatedness for both representations and classifiers in a principled way by jointly inferring their posteriors. This enables individual tasks to fully leverage inductive biases provided by related tasks, therefore improving the overall performance of all tasks. Experimental results demonstrate that the proposed VMTL is able to effectively tackle a variety of challenging multi-task learning settings with limited training data for both classification and regression. Our method consistently surpasses previous methods, including strong Bayesian approaches, and achieves state-of-the-art performance on five benchmark datasets.

Riccardo Di Sipio, Jia-Hong Huang, Samuel Yen-Chi Chen et al.

In this paper, we discuss the initial attempts at boosting understanding human language based on deep-learning models with quantum computing. We successfully train a quantum-enhanced Long Short-Term Memory network to perform the parts-of-speech tagging task via numerical simulations. Moreover, a quantum-enhanced Transformer is proposed to perform the sentiment analysis based on the existing dataset.

Devanshu Arya, Deepak K. Gupta, Stevan Rudinac et al.

Graphs are the most ubiquitous data structures for representing relational datasets and performing inferences in them. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations. This drawback is mitigated by hypergraphs, in which an edge can connect an arbitrary number of nodes. Most hypergraph learning approaches convert the hypergraph structure to that of a graph and then deploy existing geometric deep learning methods. This transformation leads to information loss, and sub-optimal exploitation of the hypergraph's expressive power. We present HyperMSG, a novel hypergraph learning framework that uses a modular two-level neural message passing strategy to accurately and efficiently propagate information within each hyperedge and across the hyperedges. HyperMSG adapts to the data and task by learning an attention weight associated with each node's degree centrality. Such a mechanism quantifies both local and global importance of a node, capturing the structural properties of a hypergraph. HyperMSG is inductive, allowing inference on previously unseen nodes. Further, it is robust and outperforms state-of-the-art hypergraph learning methods on a wide range of tasks and datasets. Finally, we demonstrate the effectiveness of HyperMSG in learning multimodal relations through detailed experimentation on a challenging multimedia dataset.

Ivona Najdenkoska, Xiantong Zhen, Marcel Worring et al.

Automating report generation for medical imaging promises to reduce workload and assist diagnosis in clinical practice. Recent work has shown that deep learning models can successfully caption natural images. However, learning from medical data is challenging due to the diversity and uncertainty inherent in the reports written by different radiologists with discrepant expertise and experience. To tackle these challenges, we propose variational topic inference for automatic report generation. Specifically, we introduce a set of topics as latent variables to guide sentence generation by aligning image and language modalities in a latent space. The topics are inferred in a conditional variational inference framework, with each topic governing the generation of a sentence in the report. Further, we adopt a visual attention module that enables the model to attend to different locations in the image and generate more informative descriptions. We conduct extensive experiments on two benchmarks, namely Indiana U. Chest X-rays and MIMIC-CXR. The results demonstrate that our proposed variational topic inference method can generate novel reports rather than mere copies of reports used in training, while still achieving comparable performance to state-of-the-art methods in terms of standard language generation criteria.

Jia-Hong Huang, Ting-Wei Wu, Chao-Han Huck Yang et al.

Automatically generating medical reports for retinal images is one of the promising ways to help ophthalmologists reduce their workload and improve work efficiency. In this work, we propose a new context-driven encoding network to automatically generate medical reports for retinal images. The proposed model is mainly composed of a multi-modal input encoder and a fused-feature decoder. Our experimental results show that our proposed method is capable of effectively leveraging the interactive information between the input image and context, i.e., keywords in our case. The proposed method creates more accurate and meaningful reports for retinal images than baseline models and achieves state-of-the-art performance. This performance is shown in several commonly used metrics for the medical report generation task: BLEU-avg (+16%), CIDEr (+10.2%), and ROUGE (+8.6%).

Athanasios Efthymiou, Stevan Rudinac, Monika Kackovic et al.

We propose ArtSAGENet, a novel multimodal architecture that integrates Graph Neural Networks (GNNs) and Convolutional Neural Networks (CNNs), to jointly learn visual and semantic-based artistic representations. First, we illustrate the significant advantages of multi-task learning for fine art analysis and argue that it is conceptually a much more appropriate setting in the fine art domain than the single-task alternatives. We further demonstrate that several GNN architectures can outperform strong CNN baselines in a range of fine art analysis tasks, such as style classification, artist attribution, creation period estimation, and tag prediction, while training them requires an order of magnitude less computational time and only a small amount of labeled data. Finally, through extensive experimentation we show that our proposed ArtSAGENet captures and encodes valuable relational dependencies between the artists and the artworks, surpassing the performance of traditional methods that rely solely on the analysis of visual content. Our findings underline a great potential of integrating visual content and semantics for fine art analysis and curation.

Jia-Hong Huang, Ting-Wei Wu, Marcel Worring

Medical image captioning automatically generates a medical description to describe the content of a given medical image. A traditional medical image captioning model creates a medical description only based on a single medical image input. Hence, an abstract medical description or concept is hard to be generated based on the traditional approach. Such a method limits the effectiveness of medical image captioning. Multi-modal medical image captioning is one of the approaches utilized to address this problem. In multi-modal medical image captioning, textual input, e.g., expert-defined keywords, is considered as one of the main drivers of medical description generation. Thus, encoding the textual input and the medical image effectively are both important for the task of multi-modal medical image captioning. In this work, a new end-to-end deep multi-modal medical image captioning model is proposed. Contextualized keyword representations, textual feature reinforcement, and masked self-attention are used to develop the proposed approach. Based on the evaluation of the existing multi-modal medical image captioning dataset, experimental results show that the proposed model is effective with the increase of +53.2% in BLEU-avg and +18.6% in CIDEr, compared with the state-of-the-art method.

Jia-Hong Huang, Luka Murn, Marta Mrak et al.

Traditional video summarization methods generate fixed video representations regardless of user interest. Therefore such methods limit users' expectations in content search and exploration scenarios. Multi-modal video summarization is one of the methods utilized to address this problem. When multi-modal video summarization is used to help video exploration, a text-based query is considered as one of the main drivers of video summary generation, as it is user-defined. Thus, encoding the text-based query and the video effectively are both important for the task of multi-modal video summarization. In this work, a new method is proposed that uses a specialized attention network and contextualized word representations to tackle this task. The proposed model consists of a contextualized video summary controller, multi-modal attention mechanisms, an interactive attention network, and a video summary generator. Based on the evaluation of the existing multi-modal video summarization benchmark, experimental results show that the proposed model is effective with the increase of +5.88% in accuracy and +4.06% increase of F1-score, compared with the state-of-the-art method.

Tom van Sonsbeek, Xiantong Zhen, Marcel Worring et al.

Disease classification relying solely on imaging data attracts great interest in medical image analysis. Current models could be further improved, however, by also employing Electronic Health Records (EHRs), which contain rich information on patients and findings from clinicians. It is challenging to incorporate this information into disease classification due to the high reliance on clinician input in EHRs, limiting the possibility for automated diagnosis. In this paper, we propose \textit{variational knowledge distillation} (VKD), which is a new probabilistic inference framework for disease classification based on X-rays that leverages knowledge from EHRs. Specifically, we introduce a conditional latent variable model, where we infer the latent representation of the X-ray image with the variational posterior conditioning on the associated EHR text. By doing so, the model acquires the ability to extract the visual features relevant to the disease during learning and can therefore perform more accurate classification for unseen patients at inference based solely on their X-ray scans. We demonstrate the effectiveness of our method on three public benchmark datasets with paired X-ray images and EHRs. The results show that the proposed variational knowledge distillation can consistently improve the performance of medical image classification and significantly surpasses current methods.

Jia-Hong Huang, Chao-Han Huck Yang, Fangyu Liu et al.

In this work, we propose an AI-based method that intends to improve the conventional retinal disease treatment procedure and help ophthalmologists increase diagnosis efficiency and accuracy. The proposed method is composed of a deep neural networks-based (DNN-based) module, including a retinal disease identifier and clinical description generator, and a DNN visual explanation module. To train and validate the effectiveness of our DNN-based module, we propose a large-scale retinal disease image dataset. Also, as ground truth, we provide a retinal image dataset manually labeled by ophthalmologists to qualitatively show, the proposed AI-based method is effective. With our experimental results, we show that the proposed method is quantitatively and qualitatively effective. Our method is capable of creating meaningful retinal image descriptions and visual explanations that are clinically relevant.

Devanshu Arya, Deepak K. Gupta, Stevan Rudinac et al.

Graphs are the most ubiquitous form of structured data representation used in machine learning. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations found in many real-world datasets. To model such complex relations, hypergraphs have proven to be a natural representation. Learning the node representations in a hypergraph is more complex than in a graph as it involves information propagation at two levels: within every hyperedge and across the hyperedges. Most current approaches first transform a hypergraph structure to a graph for use in existing geometric deep learning algorithms. This transformation leads to information loss, and sub-optimal exploitation of the hypergraph's expressive power. We present HyperSAGE, a novel hypergraph learning framework that uses a two-level neural message passing strategy to accurately and efficiently propagate information through hypergraphs. The flexible design of HyperSAGE facilitates different ways of aggregating neighborhood information. Unlike the majority of related work which is transductive, our approach, inspired by the popular GraphSAGE method, is inductive. Thus, it can also be used on previously unseen nodes, facilitating deployment in problems such as evolving or partially observed hypergraphs. Through extensive experimentation, we show that HyperSAGE outperforms state-of-the-art hypergraph learning methods on representative benchmark datasets. We also demonstrate that the higher expressive power of HyperSAGE makes it more stable in learning node representations as compared to the alternatives.

Maximilian T. Fischer, Devanshu Arya, Dirk Streeb et al.

Many processes, from gene interaction in biology to computer networks to social media, can be modeled more precisely as temporal hypergraphs than by regular graphs. This is because hypergraphs generalize graphs by extending edges to connect any number of vertices, allowing complex relationships to be described more accurately and predict their behavior over time. However, the interactive exploration and seamless refinement of such hypergraph-based prediction models still pose a major challenge. We contribute Hyper-Matrix, a novel visual analytics technique that addresses this challenge through a tight coupling between machine-learning and interactive visualizations. In particular, the technique incorporates a geometric deep learning model as a blueprint for problem-specific models while integrating visualizations for graph-based and category-based data with a novel combination of interactions for an effective user-driven exploration of hypergraph models. To eliminate demanding context switches and ensure scalability, our matrix-based visualization provides drill-down capabilities across multiple levels of semantic zoom, from an overview of model predictions down to the content. We facilitate a focused analysis of relevant connections and groups based on interactive user-steering for filtering and search tasks, a dynamically modifiable partition hierarchy, various matrix reordering techniques, and interactive model feedback. We evaluate our technique in a case study and through formative evaluation with law enforcement experts using real-world internet forum communication data. The results show that our approach surpasses existing solutions in terms of scalability and applicability, enables the incorporation of domain knowledge, and allows for fast search-space traversal. With the technique, we pave the way for the visual analytics of temporal hypergraphs in a wide variety of domains.