Luca Rossi

Amaya Gallagher-Syed, Luca Rossi, Felice Rivellese et al.

Whole Slide Images (WSIs) present a challenging computer vision task due to their gigapixel size and presence of numerous artefacts. Yet they are a valuable resource for patient diagnosis and stratification, often representing the gold standard for diagnostic tasks. Real-world clinical datasets tend to come as sets of heterogeneous WSIs with labels present at the patient-level, with poor to no annotations. Weakly supervised attention-based multiple instance learning approaches have been developed in recent years to address these challenges, but can fail to resolve both long and short-range dependencies. Here we propose an end-to-end multi-stain self-attention graph (MUSTANG) multiple instance learning pipeline, which is designed to solve a weakly-supervised gigapixel multi-image classification task, where the label is assigned at the patient-level, but no slide-level labels or region annotations are available. The pipeline uses a self-attention based approach by restricting the operations to a highly sparse k-Nearest Neighbour Graph of embedded WSI patches based on the Euclidean distance. We show this approach achieves a state-of-the-art F1-score/AUC of 0.89/0.92, outperforming the widely used CLAM model. Our approach is highly modular and can easily be modified to suit different clinical datasets, as it only requires a patient-level label without annotations and accepts WSI sets of different sizes, as the graphs can be of varying sizes and structures. The source code can be found at https://github.com/AmayaGS/MUSTANG.

Henry Senior, Gregory Slabaugh, Shanxin Yuan et al.

2D image understanding is a complex problem within computer vision, but it holds the key to providing human-level scene comprehension. It goes further than identifying the objects in an image, and instead, it attempts to understand the scene. Solutions to this problem form the underpinning of a range of tasks, including image captioning, visual question answering (VQA), and image retrieval. Graphs provide a natural way to represent the relational arrangement between objects in an image, and thus, in recent years graph neural networks (GNNs) have become a standard component of many 2D image understanding pipelines, becoming a core architectural component, especially in the VQA group of tasks. In this survey, we review this rapidly evolving field and we provide a taxonomy of graph types used in 2D image understanding approaches, a comprehensive list of the GNN models used in this domain, and a roadmap of future potential developments. To the best of our knowledge, this is the first comprehensive survey that covers image captioning, visual question answering, and image retrieval techniques that focus on using GNNs as the main part of their architecture.

Linfeng Zhang, Taoyong Cui, Dongzhan Zhou et al.

Long-range electrostatic and polarization interactions play a central role in molecular and condensed-phase systems, yet remain fundamentally incompatible with locality-based machine-learning interatomic potentials. Although modern SO(3)-equivariant neural potentials achieve high accuracy for short-range chemistry, they cannot represent the anisotropic, slowly decaying multipolar correlations governing realistic materials, while existing long-range extensions either break SO(3) equivariance or fail to maintain energy-force consistency. Here we introduce EquiEwald, a unified neural interatomic potential that embeds an Ewald-inspired reciprocal-space formulation within an irreducible SO(3)-equivariant framework. By performing equivariant message passing in reciprocal space through learned equivariant k-space filters and an equivariant inverse transform, EquiEwald captures anisotropic, tensorial long-range correlations without sacrificing physical consistency. Across periodic and aperiodic benchmarks, EquiEwald captures long-range electrostatic behavior consistent with ab initio reference data and consistently improves energy and force accuracy, data efficiency, and long-range extrapolation. These results establish EquiEwald as a physically principled paradigm for long-range-capable machine-learning interatomic potentials.

David Wegmann, Emil Stevnsborg, Søren Knudsen et al.

Advances in machine learning have enabled the creation of realistic synthetic videos known as deepfakes. As deepfakes proliferate, concerns about rapid spread of disinformation and manipulation of public perception are mounting. Despite the alarming implications, our understanding of how individuals perceive synthetic media remains limited, obstructing the development of effective mitigation strategies. This paper aims to narrow this gap by investigating human responses to visual and auditory distortions of videos and deepfake-generated visuals and narration. In two between-subjects experiments, we study whether audio-visual distortions affect cognitive processing, such as subjective credibility assessment and objective learning outcomes. A third study reveals that artifacts from deepfakes influence credibility. The three studies show that video distortions and deepfake artifacts can reduce credibility. Our research contributes to the ongoing exploration of the cognitive processes involved in the evaluation and perception of synthetic videos, and underscores the need for further theory development concerning deepfake exposure.

Amaya Gallagher-Syed, Henry Senior, Omnia Alwazzan et al.

The development of biologically interpretable and explainable models remains a key challenge in computational pathology, particularly for multistain immunohistochemistry (IHC) analysis. We present BioX-CPath, an explainable graph neural network architecture for whole slide image (WSI) classification that leverages both spatial and semantic features across multiple stains. At its core, BioX-CPath introduces a novel Stain-Aware Attention Pooling (SAAP) module that generates biologically meaningful, stain-aware patient embeddings. Our approach achieves state-of-the-art performance on both Rheumatoid Arthritis and Sjogren's Disease multistain datasets. Beyond performance metrics, BioX-CPath provides interpretable insights through stain attention scores, entropy measures, and stain interaction scores, that permit measuring model alignment with known pathological mechanisms. This biological grounding, combined with strong classification performance, makes BioX-CPath particularly suitable for clinical applications where interpretability is key. Source code and documentation can be found at: https://github.com/AmayaGS/BioX-CPath.

Chenyu Liu, Haige Li, Luca Rossi

Graph Neural Networks (GNNs) are neural networks that aim to process graph data, capturing the relationships and interactions between nodes using the message-passing mechanism. GNN quantization has emerged as a promising approach for reducing model size and accelerating inference in resource-constrained environments. Compared to quantization in LLMs, quantizing graph features is more emphasized in GNNs. Inspired by the above, we propose to leverage prompt learning, which manipulates the input data, to improve the performance of quantization-aware training (QAT) for GNNs. To mitigate the issue that prompting the node features alone can only make part of the quantized aggregation result optimal, we introduce Low-Rank Aggregation Prompting (LoRAP), which injects lightweight, input-dependent prompts into each aggregated feature to optimize the results of quantized aggregations. Extensive evaluations on 4 leading QAT frameworks over 9 graph datasets demonstrate that LoRAP consistently enhances the performance of low-bit quantized GNNs while introducing a minimal computational overhead.

Giorgia Minello, Alessandro Bicciato, Luca Rossi et al.

In this paper, we present GGSD, a novel graph generative model based on 1) the spectral decomposition of the graph Laplacian matrix and 2) a diffusion process. Specifically, we propose to use a denoising model to sample eigenvectors and eigenvalues from which we can reconstruct the graph Laplacian and adjacency matrix. Using the Laplacian spectrum allows us to naturally capture the structural characteristics of the graph and work directly in the node space while avoiding the quadratic complexity bottleneck that limits the applicability of other diffusion-based methods. This, in turn, is accomplished by truncating the spectrum, which, as we show in our experiments, results in a faster yet accurate generative process, and by designing a novel transformer-based architecture linear in the number of nodes. Our permutation invariant model can also handle node features by concatenating them to the eigenvectors of each node. An extensive set of experiments on both synthetic and real-world graphs demonstrates the strengths of our model against state-of-the-art alternatives.

Alessandro Bicciato, Luca Cosmo, Giorgia Minello et al.

Graph neural networks are increasingly becoming the framework of choice for graph-based machine learning. In this paper, we propose a new graph neural network architecture that substitutes classical message passing with an analysis of the local distribution of node features. To this end, we extract the distribution of features in the egonet for each local neighbourhood and compare them against a set of learned label distributions by taking the histogram intersection kernel. The similarity information is then propagated to other nodes in the network, effectively creating a message passing-like mechanism where the message is determined by the ensemble of the features. We perform an ablation study to evaluate the network's performance under different choices of its hyper-parameters. Finally, we test our model on standard graph classification and regression benchmarks, and we find that it outperforms widely used alternative approaches, including both graph kernels and graph neural networks.

Pierre Le Jeune, Jiaen Liu, Luca Rossi et al.

Language model deployments in consumer-facing applications introduce numerous risks. While existing research on harms and hazards of such applications follows top-down approaches derived from regulatory frameworks and theoretical analyses, empirical evidence of real-world failure modes remains underexplored. In this work, we introduce RealHarm, a dataset of annotated problematic interactions with AI agents built from a systematic review of publicly reported incidents. Analyzing harms, causes, and hazards specifically from the deployer's perspective, we find that reputational damage constitutes the predominant organizational harm, while misinformation emerges as the most common hazard category. We empirically evaluate state-of-the-art guardrails and content moderation systems to probe whether such systems would have prevented the incidents, revealing a significant gap in the protection of AI applications.

Haohua Niu, Yuxuan Yang, Lingfeng Zhang et al.

Influence maximization (IM) in real platforms is challenged by incomplete, noisy social graphs and non-stationary diffusion dynamics. We propose SP-GCRL, a social-propagation-aware graph contrastive reinforcement learning framework that learns end-to-end seed selection under partial observability.We first introduce a social-propagation-aware nonlinear diffusion function to model reinforcement/diminishing effects and probability drift under repeated exposure; we then construct dual structural views and perform contrastive learning to obtain node representations robust to missing edges and weak ties, while replacing expensive strategy metrics with a GAT-based regression surrogate to improve efficiency and scalability; finally, we use DDQN to learn an end-to-end seed selection policy on top of these representations. Experiments on multiple real-world networks show that SP-GCRL achieves significant gains over heuristic and learning-based baselines across budgets and topologies, while maintaining strong large-scale scalability.

Chenyu Liu, Luca Rossi

The accurate diagnosis of Alzheimer's disease (AD) and prognosis of mild cognitive impairment (MCI) conversion are crucial for early intervention. However, existing multimodal methods face several challenges, from the heterogeneity of input data, to underexplored modality interactions, missing data due to patient dropouts, and limited data caused by the time-consuming and costly data collection process. In this paper, we propose a novel Prompted Hypergraph Neural Network (PHGNN) framework that addresses these limitations by integrating hypergraph based learning with prompt learning. Hypergraphs capture higher-order relationships between different modalities, while our prompt learning approach for hypergraphs, adapted from NLP, enables efficient training with limited data. Our model is validated through extensive experiments on the ADNI dataset, outperforming SOTA methods in both AD diagnosis and the prediction of MCI conversion.

Henry Senior, Luca Rossi, Gregory Slabaugh et al.

It has been a longstanding goal within image captioning to move beyond a dependence on object detection. We investigate using superpixels coupled with Vision Language Models (VLMs) to bridge the gap between detector-based captioning architectures and those that solely pretrain on large datasets. Our novel superpixel approach ensures that the model receives object-like features whilst the use of VLMs provides our model with open set object understanding. Furthermore, we extend our architecture to make use of multi-resolution inputs, allowing our model to view images in different levels of detail, and use an attention mechanism to determine which parts are most relevant to the caption. We demonstrate our model's performance with multiple VLMs and through a range of ablations detailing the impact of different architectural choices. Our full model achieves a competitive CIDEr score of $136.9$ on the COCO Karpathy split.

Luca Cosmo, Giorgia Minello, Alessandro Bicciato et al.

The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a filter. While this is readily applicable to data such as images, which can be represented as regular grids in the Euclidean space, extending the convolution operator to work on graphs proves more challenging, due to their irregular structure. In this paper, we propose to use graph kernels, i.e. kernel functions that compute an inner product on graphs, to extend the standard convolution operator to the graph domain. This allows us to define an entirely structural model that does not require computing the embedding of the input graph. Our architecture allows to plug-in any type of graph kernels and has the added benefit of providing some interpretability in terms of the structural masks that are learned during the training process, similarly to what happens for convolutional masks in traditional convolutional neural networks. We perform an extensive ablation study to investigate the model hyper-parameters' impact and show that our model achieves competitive performance on standard graph classification and regression datasets.

Umberto Michieli, Edoardo Borsato, Luca Rossi et al.

The semantic segmentation of parts of objects in the wild is a challenging task in which multiple instances of objects and multiple parts within those objects must be detected in the scene. This problem remains nowadays very marginally explored, despite its fundamental importance towards detailed object understanding. In this work, we propose a novel framework combining higher object-level context conditioning and part-level spatial relationships to address the task. To tackle object-level ambiguity, a class-conditioning module is introduced to retain class-level semantics when learning parts-level semantics. In this way, mid-level features carry also this information prior to the decoding stage. To tackle part-level ambiguity and localization we propose a novel adjacency graph-based module that aims at matching the relative spatial relationships between ground truth and predicted parts. The experimental evaluation on the Pascal-Part dataset shows that we achieve state-of-the-art results on this task.

Lu Bail, Lixin Cui, Yuhang Jiao et al.

In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to transform arbitrary-sized graphs into fixed-sized backtrackless aligned grid structures and define a new spatial graph convolution operation associated with the grid structures. We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models, but also bridges the theoretical gap between traditional Convolutional Neural Network (CNN) models and spatially-based GCN models. Furthermore, the proposed BASGCN model can both adaptively discriminate the importance between specified vertices during the convolution process and reduce the notorious tottering problem of existing spatially-based GCNs related to the Weisfeiler-Lehman algorithm, explaining the effectiveness of the proposed model. Experiments on standard graph datasets demonstrate the effectiveness of the proposed model.

Lu Bai, Yuhang Jiao, Luca Rossi et al.

This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs, and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. In order to learn representative graph characteristics, a new quantum spatial graph convolution is proposed and employed to extract multi-scale vertex features, in terms of quantum information propagation between grid vertices of each graph. Since the quantum spatial convolution preserves the grid structures of the input vertices (i.e., the convolution layer does not change the original spatial sequence of vertices), the proposed QSGCNN model allows to directly employ the traditional convolutional neural network architecture to further learn from the global graph topology, providing an end-to-end deep learning architecture that integrates the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications. We demonstrate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. The proposed QSGCNN model addresses the shortcomings of information loss and imprecise information representation arising in existing GCN models associated with the use of SortPooling or SumPooling layers. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model.

Luca Rossi, Matthew J. Williams, Christoph Stich et al.

With the advent of GPS enabled smartphones, an increasing number of users is actively sharing their location through a variety of applications and services. Along with the continuing growth of Location-Based Social Networks (LBSNs), security experts have increasingly warned the public of the dangers of exposing sensitive information such as personal location data. Most importantly, in addition to the geographical coordinates of the user's location, LBSNs allow easy access to an additional set of characteristics of that location, such as the venue type or popularity. In this paper, we investigate the role of location semantics in the identification of LBSN users. We simulate a scenario in which the attacker's goal is to reveal the identity of a set of LBSN users by observing their check-in activity. We then propose to answer the following question: what are the types of venues that a malicious user has to monitor to maximize the probability of success? Conversely, when should a user decide whether to make his/her check-in to a location public or not? We perform our study on more than 1 million check-ins distributed over 17 urban regions of the United States. Our analysis shows that different types of venues display different discriminative power in terms of user identity, with most of the venues in the "Residence" category providing the highest re-identification success across the urban regions. Interestingly, we also find that users with a high entropy of their check-ins distribution are not necessarily the hardest to identify, suggesting that it is the collective behaviour of the users' population that determines the complexity of the identification task, rather than the individual behaviour.

Luca Rossi, Mirco Musolesi, Andrea Torsello

The popularity of online social media platforms provides an unprecedented opportunity to study real-world complex networks of interactions. However, releasing this data to researchers and the public comes at the cost of potentially exposing private and sensitive user information. It has been shown that a naive anonymization of a network by removing the identity of the nodes is not sufficient to preserve users' privacy. In order to deal with malicious attacks, k-anonymity solutions have been proposed to partially obfuscate topological information that can be used to infer nodes' identity. In this paper, we study the problem of ensuring k-anonymity in time-varying graphs, i.e., graphs with a structure that changes over time, and multi-layer graphs, i.e., graphs with multiple types of links. More specifically, we examine the case in which the attacker has access to the degree of the nodes. The goal is to generate a new graph where, given the degree of a node in each (temporal) layer of the graph, such a node remains indistinguishable from other k-1 nodes in the graph. In order to achieve this, we find the optimal partitioning of the graph nodes such that the cost of anonymizing the degree information within each group is minimum. We show that this reduces to a special case of a Generalized Assignment Problem, and we propose a simple yet effective algorithm to solve it. Finally, we introduce an iterated linear programming approach to enforce the realizability of the anonymized degree sequences. The efficacy of the method is assessed through an extensive set of experiments on synthetic and real-world graphs.

Luca Rossi, James Walker, Mirco Musolesi

One of the greatest concerns related to the popularity of GPS-enabled devices and applications is the increasing availability of the personal location information generated by them and shared with application and service providers. Moreover, people tend to have regular routines and be characterized by a set of "significant places", thus making it possible to identify a user from his/her mobility data. In this paper we present a series of techniques for identifying individuals from their GPS movements. More specifically, we study the uniqueness of GPS information for three popular datasets, and we provide a detailed analysis of the discriminatory power of speed, direction and distance of travel. Most importantly, we present a simple yet effective technique for the identification of users from location information that are not included in the original dataset used for training, thus raising important privacy concerns for the management of location datasets.