Xiaoqi Wang

Xiaoqi Wang, Han-Wei Shen

Recently, Graph Neural Networks (GNNs) have significantly advanced the performance of machine learning tasks on graphs. However, this technological breakthrough makes people wonder: how does a GNN make such decisions, and can we trust its prediction with high confidence? When it comes to some critical fields, such as biomedicine, where making wrong decisions can have severe consequences, it is crucial to interpret the inner working mechanisms of GNNs before applying them. In this paper, we propose a model-agnostic model-level explanation method for different GNNs that follow the message passing scheme, GNNInterpreter, to explain the high-level decision-making process of the GNN model. More specifically, GNNInterpreter learns a probabilistic generative graph distribution that produces the most discriminative graph pattern the GNN tries to detect when making a certain prediction by optimizing a novel objective function specifically designed for the model-level explanation for GNNs. Compared to existing works, GNNInterpreter is more flexible and computationally efficient in generating explanation graphs with different types of node and edge features, without introducing another blackbox or requiring manually specified domain-specific rules. In addition, the experimental studies conducted on four different datasets demonstrate that the explanation graphs generated by GNNInterpreter match the desired graph pattern if the model is ideal; otherwise, potential model pitfalls can be revealed by the explanation. The official implementation can be found at https://github.com/yolandalalala/GNNInterpreter.

Xiaoqi Wang, Jian Xiong, Hao Gao et al.

The optimization objective of regression-based blind image quality assessment (IQA) models is to minimize the mean prediction error across the training dataset, which can lead to biased parameter estimation due to potential training data biases. To mitigate this issue, we propose a regression-free framework for image quality evaluation, which is based upon retrieving locally similar instances by incorporating semantic and distortion feature spaces. The approach is motivated by the observation that the human visual system (HVS) exhibits analogous perceptual responses to semantically similar image contents impaired by identical distortions, which we term as content-distortion consistency. The proposed method constructs a hierarchical k-nearest neighbor (k-NN) algorithm for instance retrieval through two classification modules: semantic classification (SC) module and distortion classification (DC) module. Given a test image and an IQA database, the SC module retrieves multiple pristine images semantically similar to the test image. The DC module then retrieves instances based on distortion similarity from the distorted images that correspond to each retrieved pristine image. Finally, quality prediction is obtained by aggregating the subjective scores of the retrieved instances. Without training on subjective quality scores, the proposed regression-free method achieves competitive, even superior performance compared to state-of-the-art regression-based methods on authentic and synthetic distortion IQA benchmarks.

Xiaoqi Wang, Kevin Yen, Yifan Hu et al.

While a multitude of studies have been conducted on graph drawing, many existing methods only focus on optimizing a single aesthetic aspect of graph layouts, which can lead to sub-optimal results. There are a few existing methods that have attempted to develop a flexible solution for optimizing different aesthetic aspects measured by different aesthetic criteria. Furthermore, thanks to the significant advance in deep learning techniques, several deep learning-based layout methods were proposed recently. These methods have demonstrated the advantages of deep learning approaches for graph drawing. However, none of these existing methods can be directly applied to optimizing non-differentiable criteria without special accommodation. In this work, we propose a novel Generative Adversarial Network (GAN) based deep learning framework for graph drawing, called SmartGD, which can optimize different quantitative aesthetic goals, regardless of their differentiability. To demonstrate the effectiveness and efficiency of SmartGD, we conducted experiments on minimizing stress, minimizing edge crossing, maximizing crossing angle, maximizing shape-based metrics, and a combination of multiple aesthetics. Compared with several popular graph drawing algorithms, the experimental results show that SmartGD achieves good performance both quantitatively and qualitatively.

Ziwei Li, Xiaoqi Wang, Hong-You Chen et al.

Federated learning (FL) has rapidly evolved as a promising paradigm that enables collaborative model training across distributed participants without exchanging their local data. Despite its broad applications in fields such as computer vision, graph learning, and natural language processing, the development of a data projection model that can be effectively used to visualize data in the context of FL is crucial yet remains heavily under-explored. Neighbor embedding (NE) is an essential technique for visualizing complex high-dimensional data, but collaboratively learning a joint NE model is difficult. The key challenge lies in the objective function, as effective visualization algorithms like NE require computing loss functions among pairs of data. In this paper, we introduce \textsc{FedNE}, a novel approach that integrates the \textsc{FedAvg} framework with the contrastive NE technique, without any requirements of shareable data. To address the lack of inter-client repulsion which is crucial for the alignment in the global embedding space, we develop a surrogate loss function that each client learns and shares with each other. Additionally, we propose a data-mixing strategy to augment the local data, aiming to relax the problems of invisible neighbors and false neighbors constructed by the local $k$NN graphs. We conduct comprehensive experiments on both synthetic and real-world datasets. The results demonstrate that our \textsc{FedNE} can effectively preserve the neighborhood data structures and enhance the alignment in the global embedding space compared to several baseline methods.

Rumali Perera, Xiaoqi Wang, Han-wei Shen

Knowledge Graphs (KGs) are increasingly used to represent and explore complex, interconnected data across diverse domains. However, existing KG visualization systems remain limited because they fail to provide the context of user questions. They typically return only the direct query results and arrange them with force-directed layouts by treating the graph as purely topological. Such approaches overlook user preferences, ignore ontological distances and semantics, and provide no explanation for node placement. To address these challenges, we propose Context-KG, a context-aware KG visualization framework. Context-KG reframes KG visualization around ontology, context, and user intent. Using Large Language Models (LLMs), it iteratively extracts user preferences from natural language questions and context descriptions, identifying relevant node types, attributes, and contextual relations. These preferences drive a semantically interpretable, ontology-guided layout that is tailored to each query, producing type-aware regions. Context-KG also generates high-level insights unavailable in traditional methods, opening new avenues for effective KG exploration. Evaluations on real world KGs and a comprehensive user study demonstrate improved interpretability, relevance, and task performance, establishing Context-KG as a new paradigm for KG visualization.

Xiaoqi Wang, Yi Wang, Lap-Pui Chau

Egocentric video-language understanding demands both high efficiency and accurate spatial-temporal modeling. Existing approaches face three key challenges: 1) Excessive pre-training cost arising from multi-stage pre-training pipelines, 2) Ineffective spatial-temporal encoding due to manually split 3D rotary positional embeddings that hinder feature interactions, and 3) Imprecise learning objectives in soft-label multi-instance retrieval, which neglect negative pair correlations. In this paper, we introduce EVA02-AT, a suite of EVA02-based video-language foundation models tailored to egocentric video understanding tasks. EVA02-AT first efficiently transfers an image-based CLIP model into a unified video encoder via a single-stage pretraining. Second, instead of applying rotary positional embeddings to isolated dimensions, we introduce spatial-temporal rotary positional embeddings along with joint attention, which can effectively encode both spatial and temporal information on the entire hidden dimension. This joint encoding of spatial-temporal features enables the model to learn cross-axis relationships, which are crucial for accurately modeling motion and interaction in videos. Third, focusing on multi-instance video-language retrieval tasks, we introduce the Symmetric Multi-Similarity (SMS) loss and a novel training framework that advances all soft labels for both positive and negative pairs, providing a more precise learning objective. Extensive experiments on Ego4D, EPIC-Kitchens-100, and Charades-Ego under zero-shot and fine-tuning settings demonstrate that EVA02-AT achieves state-of-the-art performance across diverse egocentric video-language tasks with fewer parameters. Models with our SMS loss also show significant performance gains on multi-instance retrieval benchmarks. Our code and models are publicly available at https://github.com/xqwang14/EVA02-AT .

Yiran Zhu, Changxi Chi, Hongxin Xiang et al.

Protein inverse folding aims to design an amino acid sequence that will fold into a given backbone structure, serving as a central task in protein design. Two main paradigms have been widely explored. Template-based methods exploit database-derived structural priors and can achieve high local precision when close structural neighbors are available, but their dependence on database coverage and match quality often degrades performance on out-of-distribution (OOD) targets. Deep learning approaches, in contrast, learn general structure-to-sequence regularities and usually generalize better to new backbones. However, they struggle to capture fine-grained local structure, which can cause uncertain residue predictions and missed local motifs in ambiguous regions. We introduce Refold, a novel framework that synergistically integrates the strengths of database-derived structural priors and deep learning prediction to enhance inverse folding. Refold obtains structural priors from matched neighbors and fuses them with model predictions to refine residue probabilities. In practice, low-quality neighbors can introduce noise, potentially degrading model performance. We address this issue with a Dynamic Utility Gate that controls prior injection and falls back to the base prediction when the priors are untrustworthy. Comprehensive evaluations on standard benchmarks demonstrate that Refold achieves state-of-the-art native sequence recovery of 0.63 on both CATH 4.2 and CATH 4.3. Also, analysis indicates that Refold delivers larger gains on high-uncertainty regions, reflecting the complementarity between structural priors and deep learning predictions.

Xiaoqi Wang, Yun Zhang, Weisi Lin

Machine vision systems (MVS) are intrinsically vulnerable to performance degradation under adverse visual conditions. To address this, we propose a machine-centric image quality assessment (MIQA) framework that quantifies the impact of image degradations on MVS performance. We establish an MIQA paradigm encompassing the end-to-end assessment workflow. To support this, we construct a machine-centric image quality database (MIQD-2.5M), comprising 2.5 million samples that capture distinctive degradation responses in both consistency and accuracy metrics, spanning 75 vision models, 250 degradation types, and three representative vision tasks. We further propose a region-aware MIQA (RA-MIQA) model to evaluate MVS visual quality through fine-grained spatial degradation analysis. Extensive experiments benchmark the proposed RA-MIQA against seven human visual system (HVS)-based IQA metrics and five retrained classical backbones. Results demonstrate RA-MIQA's superior performance in multiple dimensions, e.g., achieving SRCC gains of 13.56% on consistency and 13.37% on accuracy for image classification, while also revealing task-specific degradation sensitivities. Critically, HVS-based metrics prove inadequate for MVS quality prediction, while even specialized MIQA models struggle with background degradations, accuracy-oriented estimation, and subtle distortions. This study can advance MVS reliability and establish foundations for machine-centric image processing and optimization. The model and code are available at: https://github.com/XiaoqiWang/MIQA.

Xiaoqi Wang, Yi Wang, Lap-Pui Chau

In this report, we present our champion solution for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge in CVPR 2024. Essentially, this challenge differs from traditional visual-text retrieval tasks by providing a correlation matrix that acts as a set of soft labels for video-text clip combinations. However, existing loss functions have not fully exploited this information. Motivated by this, we propose a novel loss function, Symmetric Multi-Similarity Loss, which offers a more precise learning objective. Together with tricks and ensemble learning, the model achieves 63.76% average mAP and 74.25% average nDCG on the public leaderboard, demonstrating the effectiveness of our approach. Our code will be released at: https://github.com/xqwang14/SMS-Loss/tree/main

Liangrui Pan, Boya Ji, Peng Xi et al.

Diabetic retinopathy(DR) is the main cause of blindness in diabetic patients. However, DR can easily delay the occurrence of blindness through the diagnosis of the fundus. In view of the reality, it is difficult to collect a large amount of diabetic retina data in clinical practice. This paper proposes a few-shot learning model of a deep residual network based on Earth Mover's Distance algorithm to assist in diagnosing DR. We build training and validation classification tasks for few-shot learning based on 39 categories of 1000 sample data, train deep residual networks, and obtain experience maximization pre-training models. Based on the weights of the pre-trained model, the Earth Mover's Distance algorithm calculates the distance between the images, obtains the similarity between the images, and changes the model's parameters to improve the accuracy of the training model. Finally, the experimental construction of the small sample classification task of the test set to optimize the model further, and finally, an accuracy of 93.5667% on the 3way10shot task of the diabetic retina test set. For the experimental code and results, please refer to: https://github.com/panliangrui/few-shot-learning-funds.

Xiaoqi Wang, Yun Zhang

Accurate measurement of image quality without reference signals remains a fundamental challenge in low-level visual perception applications. In this paper, we propose a global-local progressive integration model that addresses this challenge through three key contributions: 1) We develop a dual-measurement framework that combines vision Transformer (ViT)-based global feature extractor and convolutional neural networks (CNNs)-based local feature extractor to comprehensively capture and quantify image distortion characteristics at different granularities. 2) We propose a progressive feature integration scheme that utilizes multi-scale kernel configurations to align global and local features, and progressively aggregates them via an interactive stack of channel-wise self-attention and spatial interaction modules for multi-grained quality-aware representations. 3) We introduce a semantic-aligned quality transfer method that extends the training data by automatically labeling the quality scores of diverse image content with subjective opinion scores. Experimental results demonstrate that our model yields 5.04% and 5.40% improvements in Spearman's rank-order correlation coefficient (SROCC) for cross-authentic and cross-synthetic dataset generalization tests, respectively. Furthermore, the proposed semantic-aligned quality transfer further yields 2.26% and 13.23% performance gains in evaluations on single-synthetic and cross-synthetic datasets.

Xiwei Xuan, Xiaoqi Wang, Wenbin He et al.

The advances in multi-modal foundation models (FMs) (e.g., CLIP and LLaVA) have facilitated the auto-labeling of large-scale datasets, enhancing model performance in challenging downstream tasks such as open-vocabulary object detection and segmentation. However, the quality of FM-generated labels is less studied as existing approaches focus more on data quantity over quality. This is because validating large volumes of data without ground truth presents a considerable challenge in practice. Existing methods typically rely on limited metrics to identify problematic data, lacking a comprehensive perspective, or apply human validation to only a small data fraction, failing to address the full spectrum of potential issues. To overcome these challenges, we introduce VISTA, a visual analytics framework that improves data quality to enhance the performance of multi-modal models. Targeting the complex and demanding domain of open-vocabulary image segmentation, VISTA integrates multi-phased data validation strategies with human expertise, enabling humans to identify, understand, and correct hidden issues within FM-generated labels. Through detailed use cases on two benchmark datasets and expert reviews, we demonstrate VISTA's effectiveness from both quantitative and qualitative perspectives.

Peng Zhang, Xuefeng Li, Xiaoqi Wang et al.

Network visualization has traditionally relied on heuristic metrics, such as stress, under the assumption that optimizing them leads to aesthetic and informative layouts. However, no single metric consistently produces the most effective results. A data-driven alternative is to learn from human preferences, where annotators select their favored visualization among multiple layouts of the same graphs. These human-preference labels can then be used to train a generative model that approximates human aesthetic preferences. However, obtaining human labels at scale is costly and time-consuming. As a result, this generative approach has so far been tested only with machine-labeled data. In this paper, we explore the use of large language models (LLMs) and vision models (VMs) as proxies for human judgment. Through a carefully designed user study involving 27 participants, we curated a large set of human preference labels. We used this data both to better understand human preferences and to bootstrap LLM/VM labelers. We show that prompt engineering that combines few-shot examples and diverse input formats, such as image embeddings, significantly improves LLM-human alignment, and additional filtering by the confidence score of the LLM pushes the alignment to human-human levels. Furthermore, we demonstrate that carefully trained VMs can achieve VM-human alignment at a level comparable to that between human annotators. Our results suggest that AI can feasibly serve as a scalable proxy for human labelers.

Shouwei Ruan, Hanqing Liu, Yao Huang et al.

Vision Language Models (VLMs) have exhibited remarkable generalization capabilities, yet their robustness in dynamic real-world scenarios remains largely unexplored. To systematically evaluate VLMs' robustness to real-world 3D variations, we propose AdvDreamer, the first framework capable of generating physically reproducible Adversarial 3D Transformation (Adv-3DT) samples from single-view observations. In AdvDreamer, we integrate three key innovations: Firstly, to characterize real-world 3D variations with limited prior knowledge precisely, we design a zero-shot Monocular Pose Manipulation pipeline built upon generative 3D priors. Secondly, to ensure the visual quality of worst-case Adv-3DT samples, we propose a Naturalness Reward Model that provides continuous naturalness regularization during adversarial optimization, effectively preventing convergence to hallucinated or unnatural elements. Thirdly, to enable systematic evaluation across diverse VLM architectures and visual-language tasks, we introduce the Inverse Semantic Probability loss as the adversarial optimization objective, which solely operates in the fundamental visual-textual alignment space. Based on the captured Adv-3DT samples with high aggressiveness and transferability, we establish MM3DTBench, the first VQA benchmark dataset tailored to evaluate VLM robustness under challenging 3D variations. Extensive evaluations of representative VLMs with varying architectures reveal that real-world 3D variations can pose severe threats to model performance across various tasks.

Xiaoqi Wang, Clint Sebastian, Wenbin He et al.

The recent advancements in large foundation models have driven the success of open-set image segmentation, a task focused on segmenting objects beyond predefined categories. Among various prompt types (such as points, boxes, texts, and visual references), visual reference segmentation stands out for its unique flexibility and strong zero-shot capabilities. Recently, several SAM-based methods have made notable progress in this task by automatically generating prompts to guide SAM. However, these methods often generate prompts at boundaries of target regions due to suboptimal prompt encoder, which results in instability and reduced robustness. In this work, we introduce ProSAM, a simple but effective method to address the stability challenges we identified in existing SAM-based visual reference segmentation approaches. By learning a variational prompt encoder to predict multivariate prompt distributions, ProSAM avoids generating prompts that lie in unstable regions, overcoming the instability caused by less robust prompts. Our approach consistently surpasses state-of-the-art methods on the Pascal-5$^i$ and COCO-20$^i$ datasets, providing a more robust solution for visual reference segmentation.

Xiaoqi Wang, Hongyang Du, Yuehong Gao et al.

Recent advancements in large language models (LLMs) have led to their widespread adoption and large-scale deployment across various domains. However, their environmental impact, particularly during inference, has become a growing concern due to their substantial energy consumption and carbon footprint. Existing research has focused on inference computation alone, overlooking the analysis and optimization of carbon footprint in network-aided LLM service systems. To address this gap, we propose AOLO, a framework for analysis and optimization for low-carbon oriented wireless LLM services. AOLO introduces a comprehensive carbon footprint model that quantifies greenhouse gas emissions across the entire LLM service chain, including computational inference and wireless communication. Furthermore, we formulate an optimization problem aimed at minimizing the overall carbon footprint, which is solved through joint optimization of inference outputs and transmit power under quality-of-experience and system performance constraints. To achieve this joint optimization, we leverage the energy efficiency of spiking neural networks (SNNs) by adopting SNN as the actor network and propose a low-carbon-oriented optimization algorithm, i.e., SNN-based deep reinforcement learning (SDRL). Comprehensive simulations demonstrate that SDRL algorithm significantly reduces overall carbon footprint, achieving an 18.77% reduction compared to the benchmark soft actor-critic, highlighting its potential for enabling more sustainable LLM inference services.

Junqi Liu, Yun Zhang, Xiaoqi Wang et al.

Just Recognizable Difference (JRD) represents the minimum visual difference that is detectable by machine vision, which can be exploited to promote machine vision oriented visual signal processing. In this paper, we propose a Deep Transformer based JRD (DT-JRD) prediction model for Video Coding for Machines (VCM), where the accurately predicted JRD can be used reduce the coding bit rate while maintaining the accuracy of machine tasks. Firstly, we model the JRD prediction as a multi-class classification and propose a DT-JRD prediction model that integrates an improved embedding, a content and distortion feature extraction, a multi-class classification and a novel learning strategy. Secondly, inspired by the perception property that machine vision exhibits a similar response to distortions near JRD, we propose an asymptotic JRD loss by using Gaussian Distribution-based Soft Labels (GDSL), which significantly extends the number of training labels and relaxes classification boundaries. Finally, we propose a DT-JRD based VCM to reduce the coding bits while maintaining the accuracy of object detection. Extensive experimental results demonstrate that the mean absolute error of the predicted JRD by the DT-JRD is 5.574, outperforming the state-of-the-art JRD prediction model by 13.1%. Coding experiments shows that comparing with the VVC, the DT-JRD based VCM achieves an average of 29.58% bit rate reduction while maintaining the object detection accuracy.

Xiaoqi Wang, Wenbin He, Xiwei Xuan et al.

The open-vocabulary image segmentation task involves partitioning images into semantically meaningful segments and classifying them with flexible text-defined categories. The recent vision-based foundation models such as the Segment Anything Model (SAM) have shown superior performance in generating class-agnostic image segments. The main challenge in open-vocabulary image segmentation now lies in accurately classifying these segments into text-defined categories. In this paper, we introduce the Universal Segment Embedding (USE) framework to address this challenge. This framework is comprised of two key components: 1) a data pipeline designed to efficiently curate a large amount of segment-text pairs at various granularities, and 2) a universal segment embedding model that enables precise segment classification into a vast range of text-defined categories. The USE model can not only help open-vocabulary image segmentation but also facilitate other downstream tasks (e.g., querying and ranking). Through comprehensive experimental studies on semantic segmentation and part segmentation benchmarks, we demonstrate that the USE framework outperforms state-of-the-art open-vocabulary segmentation methods.

Xiaoqi Wang, Yingjie Cheng, Yaning Yang et al.

Self-supervised representation learning (SSL) on biomedical networks provides new opportunities for drug discovery. However, how to effectively combine multiple SSL models is still challenging and has been rarely explored. Therefore, we propose multi-task joint strategies of self-supervised representation learning on biomedical networks for drug discovery, named MSSL2drug. We design six basic SSL tasks inspired by various modality features including structures, semantics, and attributes in heterogeneous biomedical networks. Importantly, fifteen combinations of multiple tasks are evaluated by a graph attention-based multi-task adversarial learning framework in two drug discovery scenarios. The results suggest two important findings. (1) Combinations of multimodal tasks achieve the best performance compared to other multi-task joint models. (2) The local-global combination models yield higher performance than random two-task combinations when there are the same size of modalities. Therefore, we conjecture that the multimodal and local-global combination strategies can be treated as the guideline of multi-task SSL for drug discovery.

Xiaoqi Wang, Kevin Yen, Yifan Hu et al.

In the past decades, many graph drawing techniques have been proposed for generating aesthetically pleasing graph layouts. However, it remains a challenging task since different layout methods tend to highlight different characteristics of the graphs. Recently, studies on deep learning based graph drawing algorithm have emerged but they are often not generalizable to arbitrary graphs without re-training. In this paper, we propose a Convolutional Graph Neural Network based deep learning framework, DeepGD, which can draw arbitrary graphs once trained. It attempts to generate layouts by compromising among multiple pre-specified aesthetics considering a good graph layout usually complies with multiple aesthetics simultaneously. In order to balance the trade-off, we propose two adaptive training strategies which adjust the weight factor of each aesthetic dynamically during training. The quantitative and qualitative assessment of DeepGD demonstrates that it is capable of drawing arbitrary graphs effectively, while being flexible at accommodating different aesthetic criteria.

Weicheng Cai, Zexin Cai, Xiang Zhang et al.

A novel learnable dictionary encoding layer is proposed in this paper for end-to-end language identification. It is inline with the conventional GMM i-vector approach both theoretically and practically. We imitate the mechanism of traditional GMM training and Supervector encoding procedure on the top of CNN. The proposed layer can accumulate high-order statistics from variable-length input sequence and generate an utterance level fixed-dimensional vector representation. Unlike the conventional methods, our new approach provides an end-to-end learning framework, where the inherent dictionary are learned directly from the loss function. The dictionaries and the encoding representation for the classifier are learned jointly. The representation is orderless and therefore appropriate for language identification. We conducted a preliminary experiment on NIST LRE07 closed-set task, and the results reveal that our proposed dictionary encoding layer achieves significant error reduction comparing with the simple average pooling.

Weicheng Cai, Zexin Cai, Wenbo Liu et al.

A novel interpretable end-to-end learning scheme for language identification is proposed. It is in line with the classical GMM i-vector methods both theoretically and practically. In the end-to-end pipeline, a general encoding layer is employed on top of the front-end CNN, so that it can encode the variable-length input sequence into an utterance level vector automatically. After comparing with the state-of-the-art GMM i-vector methods, we give insights into CNN, and reveal its role and effect in the whole pipeline. We further introduce a general encoding layer, illustrating the reason why they might be appropriate for language identification. We elaborate on several typical encoding layers, including a temporal average pooling layer, a recurrent encoding layer and a novel learnable dictionary encoding layer. We conducted experiment on NIST LRE07 closed-set task, and the results show that our proposed end-to-end systems achieve state-of-the-art performance.