Graph Neural Networks (GNNs) have emerged as a dominant paradigm for graph classification. Specifically, most existing GNNs mainly rely on the message passing strategy between neighbor nodes, where the expressivity is limited by the 1-dimensional Weisfeiler-Lehman (1-WL) test. Although a number of k-WL-based GNNs have been proposed to overcome this limitation, their computational cost increases rapidly with k, significantly restricting the practical applicability. Moreover, since the k-WL models mainly operate on node tuples, these k-WL-based GNNs cannot retain fine-grained node- or edge-level semantics required by attribution methods (e.g., Integrated Gradients), leading to the less interpretable problem. To overcome the above shortcomings, in this paper, we propose a novel Line Graph Aggregation Network (LGAN), that constructs a line graph from the induced subgraph centered at each node to perform the higher-order aggregation. We theoretically prove that the LGAN not only possesses the greater expressive power than the 2-WL under injective aggregation assumptions, but also has lower time complexity. Empirical evaluations on benchmarks demonstrate that the LGAN outperforms state-of-the-art k-WL-based GNNs, while offering better interpretability.

Hyperedge prediction plays a central role in hypergraph learning, enabling the inference of high-order relations among multiple entities. However, existing methods often rely on a simplistic flat set assumption, treating candidate hyperedges as unstructured collections of nodes and neglecting their potential internal compositionality. Furthermore, the severe scarcity of observed hyperedges poses a challenge for effective supervision. In this work, we propose S3Hyper, a Substructure-contextualized Self-Supervised framework for Hyperedge prediction, which jointly addresses these two challenges. Specifically, we design a substructure-contextualized hyperedge aggregator that models the internal hierarchy of candidate hyperedges by leveraging sub-hyperedge information. In parallel, we introduce an adaptive tri-directional contrastive learning module that incorporates node-level, hyperedge-level, and cross-level alignment objectives, supported by temperature-adaptive mechanisms. Experimental results on four public datasets demonstrate that S3Hyper consistently outperforms strong baselines, with ablation studies verifying the effectiveness of each component.

Hypergraphs provide a natural and expressive framework for modeling high-order relationships, enabling the representation of group-wise interactions beyond pairwise connections. While hypergraph neural networks (HNNs) have shown promise for learning on such structures, existing models often rely on shallow message passing and lack the ability to extract multiscale patterns. Framelet-based techniques offer a principled solution by decomposing signals into multiple frequency bands. However, most prior framelet systems, particularly Haar-type ones, are sensitive to node ordering and fail to ensure consistent representations under permutation, leading to instability in hypergraph learning. To address this, we propose Permutation Equivariant Framelet-based Hypergraph Neural Networks (PEF-HNN), a novel framework that integrates multiscale framelet analysis with permutation-consistent learning. We construct a new family of permutation equivariant Haar-type framelets specifically designed for hypergraphs, supported by theoretical analysis of their stability and decomposition properties. Built upon these framelets, PEF-HNN incorporates both low-pass and high-pass components across multiple scales into a unified neural architecture. Extensive experiments on nine benchmark datasets, including three homophilic and four heterophilic hypergraphs, as well as two real-world datasets for visual object classification, demonstrate the effectiveness of our approach, consistently outperforming existing HNN baselines and highlighting the advantages of permutation equivariant framelet design in hypergraph representation learning.

Session-based recommendation aims to predict users’ next actions by modeling their ongoing interaction sequences, particularly in scenarios where long-term user profiles are unavailable. While existing methods have achieved promising results by leveraging sequential and graph-based structures, they often rely on global aggregation strategies that emphasize dominant user interests while overlooking the transient and fine-grained behavior patterns embedded in sessions. In practice, user intent evolves across sessions and is reflected through diverse behavioral patterns, ranging from immediate preferences to segmented co-occurrence interests and long-range goals. To address these limitations, we propose GraphFine, a novel multi-granular graph learning framework that achieves fine-grained behavioral pattern awareness for session-based recommendation. Our approach models user behavior at different temporal and semantic granularities through a combination of graph and hypergraph neural networks. Specifically, we employ a position-aware graph to capture short-term item transitions, and construct segmented co-occurrence hypergraphs to uncover high-order semantic relations among co-occurred items. To preserve diverse user intents, we further introduce a multi-view intent readout mechanism that extracts and adaptively integrates intent signals from short-term actions, segmented co-occurrence patterns, and entire sessions. Extensive experiments on benchmark datasets demonstrate that GraphFine consistently outperforms existing state-of-the-art methods, confirming its effectiveness in capturing fine-grained and dynamic user preferences for more accurate recommendation.

Hyperedge prediction plays a critical role in high-order relational modeling with hypergraphs, yet most existing methods primarily focus on sampling strategies or local aggregation within candidate hyperedges. These approaches often overlook global structural dependencies that are essential for learning expressive node and hyperedge representations. In this paper, we propose HyperNoRA, a novel self-supervised hypergraph learning framework that integrates global node-level relation awareness with contrastive learning. Specifically, we construct a global node relation graph that captures both direct and indirect structural correlations, which guides a structure-aware aggregator to enhance node representations with informative global context. To prevent over-smoothing and maintain discriminability, a contrastive learning module is introduced to align representations across graph augmentations while separating semantically dissimilar nodes. Extensive experiments on several benchmark datasets demonstrate that HyperNoRA consistently outperforms state-of-the-art baselines, and ablation studies verify the effectiveness of its key components.

Unsupervised hypergraph representation learning has recently gained traction for its ability to model complex high-order interactions without requiring labeled data. However, existing contrastive learning methods typically overlook the frequency diversity inherent in hypergraph signals. To address this issue, we propose HyperAim, a contrastive learning framework that integrates adaptive multi-frequency filtering through both decoupled and coupled designs. Specifically, HyperAim employs two decoupled channels with polynomial low-pass and high-pass filters to separately capture distinct frequency components, and a third channel based on framelet decomposition that adaptively fuses multi-frequency signals in a coupled manner. A frequency-aware contrastive learning strategy is introduced to align representations across views using a combination of InfoNCE loss and pseudo-label-guided supervision. Extensive experiments across 12 benchmark datasets, covering both homophilic and heterophilic hypergraphs, demonstrate the consistent superiority of HyperAim over 17 baselines. Ablation studies further confirm the benefits of explicitly modeling and aligning frequency-specific representations.

In this paper, we develop a novel local graph pooling method, namely the Separated Subgraph-based Hierarchical Pooling (SSHPool), for graph classification. We commence by assigning the nodes of a sample graph into different clusters, resulting in a family of separated subgraphs. We individually employ the local graph convolution units as the local structure to further compress each subgraph into a coarsened node, transforming the original graph into a coarsened graph. Since these subgraphs are separated by different clusters and the structural information cannot be propagated between them, the local convolution operation can significantly avoid the over-smoothing problem caused by message passing through edges in most existing Graph Neural Networks (GNNs). By hierarchically performing the proposed procedures on the resulting coarsened graph, the proposed SSHPool can effectively extract the hierarchical global features of the original graph structure, encapsulating rich intrinsic structural characteristics. Furthermore, we develop an end-to-end GNN framework associated with the SSHPool module for graph classification. Experimental results demonstrate the superior performance of the proposed model on real-world datasets.

Safety-aligned large language models (LLMs) often generate refusal responses to harmless queries due to the over-refusal problem.However, existing methods for mitigating overrefusal cannot maintain a low refusal ratio for harmless queries while keeping a high refusal ratio for malicious ones.In this paper, we analyze how system prompts with varying safety levels affect LLM refusal behaviors when facing over-refusal queries.A key observation is that, when LLMs suffer from the over-refusal issue, non-refusal tokens remain present in the next-token candidate list, but the model systematically fails to select them, despite the generation of refusal tokens.Based on this observation, we propose a trainingfree and model-agnostic approach, Adaptive Contrastive Decoding (AdaCD), to mitigate over-refusal while maintaining LLM safety.First, AdaCD compares the output distributions of the LLM with or without an extreme safety system prompt to refine the refusal token distribution.Second, we introduce an adaptive contrastive decoding strategy that dynamically incorporates or removes the refusal token distribution, adaptively boosting the probability of selecting refusal or non-refusal tokens.Experimental results on five benchmark datasets show that, on average, AdaCD reduces the refusal ratio for over-refusal queries by 10.35%, yet still increases the refusal ratio for malicious queries by 0.13%.

Large language models (LLMs) are increasingly adopted as the backbone of recommender systems. However, user–item interactions in real-world scenarios are non-stationary, making preference drift over time inevitable. Existing model update strategies mainly rely on global fine-tuning or pointwise editing, but they face two fundamental challenges: (i) imbalanced update granularity, where global updates perturb behaviors unrelated to the target while pointwise edits fail to capture broader preference shifts; (ii) unstable incremental updates, where repeated edits interfere with prior adaptations, leading to catastrophic forgetting and inconsistent recommendations. To address these issues, we propose Region-Aware Incremental Editing (RAIE), a plug-in framework that freezes the backbone model and performs region-level updates. RAIE first constructs semantically coherent preference regions via spherical k-means in the representation space. It then assigns incoming sequences to regions via confidence-aware gating and performs three localized edit operations-Update, Expand, and Add-to dynamically revise the affected region. Each region is equipped with a dedicated Low-Rank Adaptation (LoRA) module, which is trained only on the region's updated data. During inference, RAIE routes each user sequence to its corresponding region and activates the region-specific adapter for prediction. Experiments on two benchmark datasets under a time-sliced protocol that segments data into Set-up (S), Finetune (F), and Test (T) show that RAIE significantly outperforms state-of-the-art baselines while effectively mitigating forgetting. These results demonstrate that region-aware editing offers an accurate and scalable mechanism for continual adaptation in dynamic recommendation scenarios.

The knowledge tracing (KT) aims to track changes in students' knowledge status and predict their future answers based on their historical answer records. Current research on KT modeling focuses on predicting student' future performance based on existing, unupdated records of student learning interactions. However, these approaches ignore the distractors (such as slipping and guessing) in the answering process and overlook that static cognitive representations are temporary and limited. Most of them assume that there are no distractors in the answering process and that the record representations fully represent the students' level of understanding and proficiency in knowledge. In this case, it may lead to many lack of synergy and incoordination issue in the original records. Therefore we propose a cognitive representation optimization for KT (CRO-KT) model, which utilizes a dynamic programming algorithm to optimize structure of cognitive representations. This ensures that the structure matches the students' cognitive patterns in terms of the difficulty of the exercises. Furthermore, we use the co-optimization algorithm to optimize the cognitive representations of the subtarget exercises in terms of the overall situation of exercises responses by considering all the exercises with co-relationships as a single goal. Meanwhile, the CRO-KT model fuses the learned relational embeddings from the bipartite graph with the optimized record representations in a weighted manner, enhancing the expression of students' cognition. Finally, experiments are conducted on three publicly available datasets respectively to validate the effectiveness of the proposed cognitive representation optimization model. The source code of CRDP-KT is available at https://github.com/bigdata-graph/CRO-KT.

Chinese calligraphy is a quintessential element of Chinese cultural heritage. Analyzing and comparing calligraphic styles not only enhances the appreciation, learning, and advancement of calligraphy but also provides valuable insights into ancient China. However, such analysis remains challenging due to the limited scalability and possible inconsistencies of qualitative methods, as well as usability and misalignment issues in conventional quantitative approaches. We propose Calli-VA, a visual analytics system, to address these challenges. Calli-VA extracts character images and their corresponding strokes from original works and characterizes each character using systematic criteria. During analysis, the system defines the analysis scope by overview and uncovers relationships between characters. Explanation and recommendation mechanisms are integrated to help users understand patterns and guide further exploration. A documentation feature allows users to record and share their findings. We demonstrate the effectiveness of Calli-VA through three case studies and expert feedback.

Hypergraphs provide a flexible framework for modeling high-order (complex) interactions among multiple entities, extending beyond traditional pairwise correlations in graph structures. However, deep hypergraph neural networks (HGNNs) often face the challenge of oversmoothing with increasing depth, similar to issues in graph neural networks (GNNs). While oversmoothing in GNNs has been extensively studied, its implications in relation to hypergraphs are less explored. This paper addresses this gap by first theoretically exploring the reasons behind oversmoothing in deep HGNNs. Our novel insights suggest that a spectral-based hypergraph convolution, equipped with both low-pass and high-pass filters, can potentially mitigate these effects. Motivated by these findings, we introduce FrameHGNN, a framework that utilizes framelet-based hypergraph convolutions integrating tight framelet transforms with both low-pass and high-pass components, as well as the commonly used strategies in designing deep GNN architecture: initial residual and identity mappings. The experiment results on diverse benchmark datasets demonstrate that FrameHGNN outperforms several state-of-the-art models, effectively reducing oversmoothing while improving predictive accuracy. Our contributions not only advance the theoretical understanding of deep hypergraph learning but also provide a practical spectral-based approach for HGNNs, emphasizing the design of multifrequency channels.

Hypergraph neural networks (HNNs) have shown promise in handling tasks characterized by high-order correlations, achieving notable success across various applications. However, there has been limited focus on heterophilic hypergraph learning (HHL), in contrast to the increasing attention given to graph neural networks designed for graphs exhibiting heterophily. This paper aims to pave the way for HHL by addressing key gaps from multiple perspectives: measurement, dataset diversity, and baseline model development. First, we introduce metrics to quantify heterophily in hypergraphs, providing a numerical basis for assessing the homophily/heterophily ratio. Second, we develop diverse benchmark datasets across various real-world scenarios, facilitating comprehensive evaluations of existing HNNs and advancing research in HHL. Additionally, as a novel baseline model, we propose HyperUFG, a framelet-based HNN integrating both low-pass and high-pass filters. Extensive experiments conducted on synthetic and benchmark datasets highlight the challenges current HNNs face with heterophilic hypergraphs, while showcasing that HyperUFG performs competitively and often outperforms many existing models in such scenarios. Overall, our study underscores the urgent need for further exploration and development in this emerging field, with the potential to inspire and guide future research in HHL.

Graph-based representations are powerful tools for analyzing structured data. In this paper, we propose a novel model to learn Deep Hierarchical Attention-based Kernelized Representations (DHAKR) for graph classification. To this end, we commence by learning an assignment matrix to hierarchically map the substructure invariants into a set of composite invariants, resulting in hierarchical kernelized representations for graphs. Moreover, we introduce the feature-channel attention mechanism to capture the interdependencies between different substructure invariants that will be converged into the composite invariants, addressing the shortcoming of discarding the importance of different substructures arising in most existing R-convolution graph kernels. We show that the proposed DHAKR model can adaptively compute the kernel-based similarity between graphs, identifying the common structural patterns over all graphs. Experiments demonstrate the effectiveness of the proposed DHAKR model.

This paper proposes a family of Aligned Entropic Graph Kernels (AEGK) for graph classification, based on the Averaged Mixing Matrix (AMM) of Continuous-time Quantum Walks (CTQWs). Specifically, we show how the AMM matrix allows us to compute a quantum Shannon entropy of each vertex for either un-attributed or attributed graphs. For pairwise graphs, the proposed AEGK kernels are defined by computing the kernel-based similarity between the quantum Shannon entropies of their pairwise aligned vertices. Theoretical analysis reveals that the AEGK kernels can not only integrate the structural correspondence information between graphs, but also discriminate the structural differences between aligned vertices. Moreover, the AEGK kernels can simultaneously capture both global and local structural characteristics through the quantum Shannon entropies. These theoretical properties explain the effectiveness.

This paper proposes a family of Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK) for un-attributed graphs. The HAQJSK kernels can incorporate hierarchical correspondence information between graphs, and thus transform arbitrary sized graphs into fix-sized aligned structures, i.e., the hierarchical transitive aligned Adjacency Matrix of vertices or Density Matrix of Continuous-Time Quantum Walks (CTQWs). For pairwise graphs, the resulting HAQJSK kernels are defined by computing the Quantum Jensen-Shannon Divergence (QJSD) between their aligned structures. Unlike classical graph kernels, the HAQJSK kernels can either reflect global intrinsic structure characteristics through CTQWs, or address the drawback of neglecting structural correspondence information, theoretically explaining the effectiveness.

As large language models (LLMs)-driven conversational systems have advanced, users have become accustomed to engaging in standalone, continuous interactions. In such interactions, users may abruptly change their intent across turns. However, most existing intent detection methods focus on accurately extracting intents and slots from individual utterances, without considering the broader conversational dynamics. This makes them ill-equipped to handle long, evolving conversations where arbitrary intent drift can occur. To address this challenge, we define the intent drift detection task in continuous conversations. We then propose a differentiable method, termed DriftHunter, that enables neural networks to understand how user intent shifts as the conversation progresses via dynamically accumulating the temporal transition across turns. Unlike existing methods, our proposed method incrementally captures global and local transition patterns between intents and slots without relying on prior statistical results. Moreover, our model sequentially accumulates transition patterns across conversation turns. This allows it to learn temporal accumulated dynamics, enabling neural network models to better focus on the most trending user intents during continuous interaction. Experimental evaluations on real-world datasets demonstrate that the proposed method outperforms state-of-the-art baselines in both intent drift detection, intent identification, and slot-filling downstream tasks. Our case study analysis reveals that the learned temporal transition patterns explain the predicted intent drifts.11The source code and dataset are available at https://github.com/FDHTJ/DriftHunter

The growing demand for personalized learning underscores the importance of accurately predicting students’ future performance to support tailored education and optimize instructional strategies. Traditional approaches predominantly focus on temporal modeling using historical response records and learning trajectories. While effective, these methods often fall short in capturing the intricate interactions between students and learning content, as well as the subtle semantics of these interactions. To address these gaps, we present EduLLM, the first framework to leverage large language models in combination with hypergraph learning for student performance prediction. The framework incorporates FraS-HNN ($\underline{\mbox{Fra}}$melet-based $\underline{\mbox{S}}$igned $\underline{\mbox{H}}$ypergraph $\underline{\mbox{N}}$eural $\underline{\mbox{N}}$etworks), a novel spectral-based model for signed hypergraph learning, designed to model interactions between students and multiple-choice questions. In this setup, students and questions are represented as nodes, while response records are encoded as positive and negative signed hyperedges, effectively capturing both structural and semantic intricacies of personalized learning behaviors. FraS-HNN employs framelet-based low-pass and high-pass filters to extract multi-frequency features. EduLLM integrates fine-grained semantic features derived from LLMs, synergizing with signed hypergraph representations to enhance prediction accuracy. Extensive experiments conducted on multiple educational datasets demonstrate that EduLLM significantly outperforms state-of-the-art baselines, validating the novel integration of LLMs with FraS-HNN for signed hypergraph learning.

With the growing adoption of Hypergraph Neural Networks (HNNs) to model higher-order relationships in complex data, concerns about their security and robustness have become increasingly important. However, current security research often overlooks the unique structural characteristics of hypergraph models when developing adversarial attack and defense strategies. To address this gap, we demonstrate that hypergraphs are particularly vulnerable to node injection attacks, which align closely with real-world applications. Through empirical analysis, we develop a relatively unnoticeable attack approach by monitoring changes in homophily and leveraging this self-regulating property to enhance stealth. Building on these insights, we introduce HyperNear, i.e., $\underline{N}$ode inj$\underline{E}$ction $\underline{A}$ttacks on hype$\underline{R}$graph neural networks, the first node injection attack framework specifically tailored for HNNs. HyperNear integrates homophily-preserving strategies to optimize both stealth and attack effectiveness. Extensive experiments show that HyperNear achieves excellent performance and generalization, marking the first comprehensive study of injection attacks on hypergraphs. Our code is available at https://github.com/ca1man-2022/HyperNear.

Graph Neural Networks (GNNs) have emerged as powerful tools for graph learning, and one key challenge arising in GNNs is the development of effective pooling operations for learning meaningful graph representations. In this paper, we propose a novel Edge-Node Attention-based Hierarchical Pooling (ENAHPool) operation for GNNs. Unlike existing cluster-based pooling methods that suffer from ambiguous node assignments and uniform edge-node information aggregation, ENAHPool assigns each node exclusively to a cluster and employs attention mechanisms to perform weighted aggregation of both node features within clusters and edge connectivity strengths between clusters, resulting in more informative hierarchical representations. To further enhance the model performance, we introduce a Multi-Distance Message Passing Neural Network (MD-MPNN) that utilizes edge connectivity strength information to enable direct and selective message propagation across multiple distances, effectively mitigating the over-squashing problem in classical MPNNs. Experimental results demonstrate the effectiveness of the proposed method.

In this paper, we propose a new model to learn Adaptive Kernel-based Representations (AKBR) for graph classification. Unlike state-of-the-art R-convolution graph kernels that are defined by merely counting any pair of isomorphic substructures between graphs and cannot provide an end-to-end learning mechanism for the classifier, the proposed AKBR approach aims to define an end-to-end representation learning model to construct an adaptive kernel matrix for graphs. To this end, we commence by leveraging a novel feature-channel attention mechanism to capture the interdependencies between different substructure invariants of original graphs. The proposed AKBR model can thus effectively identify the structural importance of different substructures, and compute the R-convolution kernel between pairwise graphs associated with the more significant substructures specified by their structural attentions. Furthermore, the proposed AKBR model employs all sample graphs as the prototype graphs, naturally providing an end-to-end learning architecture between the kernel computation as well as the classifier. Experimental results show that the proposed AKBR model outperforms existing state-of-the-art graph kernels and deep learning methods on standard graph benchmarks.

The over-smoothing has emerged as a major challenge in the development of Graph Neural Networks (GNNs). While existing state-of-the-art methods effectively mitigate the diminishing distance between nodes and improve the performance of node classification, they tend to be elusive for graph-level tasks. This paper introduces a novel entropy-based perspective to explore the over-smoothing problem, simultaneously enhancing the distinguishability of non-isomorphic graphs. We provide a theoretical analysis of the relationship between the smoothness and the entropy for graphs, highlighting how the over-smoothing in high-entropic regions negatively impact the graph classification performance. To tackle this issue, we propose a simple yet effective method to Sample and Discretize node features in high-Entropic regions (SDE), aiming to preserve the critical and complicated structural information. Moreover, we introduce a new evaluation metric to assess the over-smoothing for graph-level tasks, focusing on node distributions. Experimental results demonstrate that the proposed SDE method significantly outperforms existing state-of-the-art methods, establishing a new benchmark in the field of GNNs.

In this paper, we propose a Hierarchical Aligned Subtree Convolutional Network (HA-SCN) for graph classification. Our idea is to transform graphs of arbitrary sizes into fixed-sized aligned graphs and construct a normalized K-layer m-ary subtree for each node in the aligned graphs. By sliding convolutional filters over the entire subtree at each node, we define a novel subtree convolution and pooling operation that hierarchically abstracts node-level information. We demonstrate that the proposed HA-SCN model not only realizes the convolution mechanism similar to the Convolutional Neural Networks (CNNs), which have the characteristics of weight sharing and fixed-sized receptive fields, but also effectively mitigates the over-squashing problem. Meanwhile, it establishes the correspondence information between nodes, alleviating the information loss issue. Experimental results on various benchmark graph datasets show that our approach achieves state-of-the-art performance in graph classification tasks.

In this paper, we propose a family of novel Deep Hierarchical Transitive-Aligned Graph Kernels (DHTAGK) for graph classification. To this end, we commence by developing a new Hierarchical Aligned Graph Auto-Encoder (HA-GAE) to construct transitive-aligned embedding graphs that encapsulate the structural correspondence information between graphs. The DHTAGK kernels then measure either the Jensen-Shannon Divergence between the adjacency matrices or the Gaussian kernel between the node feature matrices of the embedding graphs. Unlike the classical R-convolution kernels and node-based alignment kernels, the DHTAGK kernels can capture the transitive structural correspondence information and thus ensure the positive definiteness. Furthermore, the HA-GAE enables the DHTAGK kernels to simultaneously reflect both local and global graph structures and identify common structural patterns. Experimental results show that the DHTAGK kernels outperform state-of-the-art graph kernels and deep learning methods on benchmark datasets.

Multimodal emotion recognition aims to identify emotions by integrating multimodal features derived from spoken utterances. However, existing work often neglects the calibration of conversational entities, focusing mainly on extracting potential intra- or cross-modal information. This leads to the underutilization of utterance information that is essential for accurately characterizing emotion. Additionally, the lack of effective modeling of conversational patterns limits the ability to capture emotional pathways across contexts, modalities and speakers, impacting the overall emotional understanding. In this study, we propose the modality-calibrated hypergraph fusion network (MATCH), which leverages multimodal fusion and hypergraph learning techniques to address these challenges. In particular, we introduce an entity calibration strategy that refines the representations of conversational entities both at the modality and context levels, allowing for deeper insights into emotion-related cues. Furthermore, we present an emotion-aligned hypergraph fusion method that incorporates a line graph to explore conversational patterns, facilitating flexible knowledge transfer across modalities through hyperedge-level and graph-level alignments. Experiments demonstrate that MATCH outperforms state-of-the-art approaches on two benchmark datasets.

Graph Neural Networks (GNNs) are powerful tools for graph learning, but one of the important challenges is how to effectively extract representations for graph-level tasks. In this paper, we propose an end-to-end Simple Clustering Hierarchical Pooling (SCHPool) operation, which is based on Top-K node selection for learning expressive graph representations. Specifically, SCHPool considers each node and its local neighborhood as a cluster, and introduces a novel multi-view scoring function to evaluate node importance. Based on these scores, clusters centered around the Top-K nodes are retained. This design eliminates the need for complex clustering operations, significantly reducing computational overhead. Furthermore, during the coarsening process, SCHPool employs a lightweight yet comprehensive attention mechanism to adaptively aggregate both the node features within clusters and the edge connectivity strengths between clusters. This facilitates the construction of more informative coarsened graphs, enhancing model performance. Experimental results demonstrate the effectiveness of the proposed model.

In recent years, the out-of-distribution (OOD) generalization problem of graph data has received widespread attention, which refers to how a model maintains strong generalization performance when there are distribution shifts between training and testing data. Invariant learning is considered as an effective solution for solving the OOD generalization problem. However, graph data has more complex structures than Euclidean data and contains a variety of distribution shifts. Therefore, the captured invariant features may include spurious invariant components, which can drop the generalization performance of the model. To solve this problem, we propose a new invariant learning model named causal information bottleneck learning model (CIBL). Specifically, we introduce information bottleneck principle to eliminate the impact of spurious invariant components on the model by compressing the learned redundant information. In this way, the model can learn causal invariant features, which can ensure the generalization performance of the model. We conduct several experiments in different OOD scenarios, and the results demonstrate that the CIBL model outperforms other baseline models.

Graph contrastive learning (GraphCL) is widely used in recommendation systems. However, GraphCL recommendation systems are still plagued by the popularity bias problem. Besides, during the contrastive task, data augmentation may damage the original data structure information. To solve these problems, we propose a new GraphCL recommendation model, namely GCR-DDA, which contains three key modules: collaborative relation encoder (CRE), debiasing channel and structure preserving channel. The CRE is used to integrate local neighborhood information. In the debiasing channel, noise-based embedding augmentation is designed to mitigate the popularity bias problem of the skewed distribution. In the structure preserving channel, the variational graph auto-encoder (VGAE) is implied as a graph generation model for data augmentation. Contrastive task is constructed from the two channels, and is integrated with the recommendation task in a joint optimization model. Results of extensive experiments on three datasets show that GCR-DDA outperforms baselines.

The problem of over-smoothing has emerged as a fundamental issue for Graph Convolutional Networks (GCNs). While existing efforts primarily focus on enhancing the discriminability of node representations for node classification, they tend to overlook the over-smoothing at the graph level, significantly influencing the performance of graph classification. In this paper, we provide an explanation of the graph-level over-smoothing phenomenon and propose a novel Adaptive Multi-Viewed Subgraph Convolutional Network (MultiNet) to address this challenge. Specifically, the MultiNet introduces a local subgraph convolution module that adaptively divides each input graph into multiple subgraph views. Then a number of subgraph-based view-specific convolution operations are applied to constrain the extent of node information propagation over the original global graph structure, not only mitigating the over-smoothing issue but also generating more discriminative local node representations. Moreover, we develop an alignment-based readout that establishes correspondences between nodes over different graphs, thereby effectively preserving the local node-level structure information and improving the discriminative ability of the resulting graph-level representations. Theoretical analysis and empirical studies show that the MultiNet mitigates the graph-level over-smoothing and achieves excellent performance for graph classification.

Large Language Models (LLMs) have revolutionized recommender systems by offering highly personalized and context-aware suggestions. However, their inherent biases pose significant challenges in sensitive scenarios like job recommendation, potentially compromising fairness and resulting in harmful effects on both users and platforms. While previous studies have explored fairness issues in LLM-based job recommendations, they often focus on limited dimensions. We introduce FairWork, a comprehensive fairness evaluation framework to examine LLM-based recommender system from both the user's and recruiter's perspectives, employing fairness metrics to assess how sensitive user attributes influence job recommendations. The system allows stakeholders such as recruitment platforms and job seekers to upload personalized profiles and job descriptions for fairness analysis. By integrating specific job requirements and user-driven data inputs, FairWork captures the relationship between candidate qualifications and job demands. This framework provides a robust foundation for evaluating fairness in LLM-based job recommender systems and supports future research on bias mitigation strategies. The demo is available at https://github.com/chenzhouli/FairWork.

Existing Graph Attention Networks (GATs) generally adopt the self-attention mechanism to learn graph edge attention, which usually return dense attention coefficients over all neighbors and thus are prone to be sensitive to graph edge noises. To overcome this problem, sparse GATs are desirable and have garnered increasing interest in recent years. However, existing sparse GATs usually suffer from high training complexity and are also not straightforward for inductive learning tasks. To address these issues, we propose to learn sparse GATs by exploiting spiking neuron (SN) mechanism, termed Graph Spiking Attention (GSAT). Specifically, it is known that spiking neuron can perform inexpensive information processing by transmitting the input data into discrete spike trains and return sparse outputs. Inspired by it, this work attempts to exploit spiking neuron to learn sparse attention coefficients, resulting in edge-sparsified graph for GNNs. Therefore, GSAT can perform message passing on the selective neighbors naturally, which makes GSAT perform compactly and robustly w.r.t graph noises. Moreover, GSAT can be used straightforwardly for inductive learning tasks. Extensive experiments on both transductive and inductive tasks demonstrate the effectiveness, robustness and efficiency of GSAT.

Infrared and visible image fusion aims to extract complementary features to synthesize a single fused image. In our method, we covert the regular image format into the graph space and conduct graph convolutional networks (GCNs) to extract NLss for the reliable infrared and visible image fusion. More specifically, GCNs are first performed on each intra-modal set to aggregate the features and propagate the inherent information, thereby extracting independent intra-modal NLss. Then, such intra-modal non-local self-similarity (NLss) features of infrared and visible images are concatenated to explore cross-domain NLss inter-modally and reconstruct the fused images. Extensive experiments show the superior performance of our method with the qualitative and quantitative analysis on the TNO, RoadScene and M3FD datasets, respectively, outperforming many state-of-the-art (SOTA) methods for the robust and effective infrared and visible image fusion.

Infrared and visible image fusion (IVF) plays an important role in intelligent transportation system (ITS). The early works predominantly focus on boosting visual appeal of the fused result, although several recent approaches have tried to combine high-level vision task with IVF, they prioritize the design of cascaded structure to seek unified suitable features and fit different tasks. Thus, they tend to bias toward reconstructing raw pixels without considering the significance of semantic features. Therefore, we propose a novel prior semantic guided image fusion method based on the dual-modality strategy, improving the performance of IVF in ITS. Specifically, to explore the independent significant semantic of each modality, we first design two parallel semantic segmentation branches with a refined feature adaptive-modulation (RFaM) mechanism. RFaM can perceive the features that are semantically distinct enough in each semantic segmentation branch. Then, two pilot experiments based on the two branches are conducted to capture the significant prior semantic of source images, which is then applied to guide the fusion task in the integration of semantic segmentation branches and fusion branch. In addition, to aggregate both high-level semantics and impressive visual effects, we further investigate the frequency response of the prior semantics, and propose a multi-level representation-adaptive fusion (MRaF) module to explicitly integrate low-frequency prior semantic with high-frequency details. Extensive experiments on two public datasets demonstrate the superiority of our method over state-of-the-art fusion approaches. Our method has better performance on four quantitative metrics in fusion task and achieves the highest mIoU in semantic segmentation task.

In this work, we develop a family of Aligned Entropic Graph Kernels (AEGK) for graph classification. We commence by performing the Continuous-time Quantum Walk (CTQW) on each graph structure, and compute the Averaged Mixing Matrix (AMM) to describe how the CTQW visits all vertices from a starting vertex. More specifically, we show how this AMM matrix allows us to compute a quantum Shannon entropy of each vertex for either un-attributed or attributed graphs. For pairwise graphs, the proposed AEGK kernels are defined by computing the kernel-based similarity between the quantum Shannon entropies of their pairwise aligned vertices. The analysis of theoretical properties reveals that the proposed AEGK kernels cannot only address the shortcoming of neglecting the structural correspondence information between graphs arising in most existing R-convolution graph kernels, but also overcome the problems of neglecting the structural differences and vertex-attributed information arising in existing vertex-based matching kernels. Moreover, unlike most existing classical graph kernels that only focus on the global or local structural information of graphs, the proposed AEGK kernels can simultaneously capture both global and local structural characteristics through the quantum Shannon entropies, reflecting more precise kernel-based similarity measures between pairwise graphs. The above theoretical properties explain the effectiveness of the proposed AEGK kernels. Experimental evaluations demonstrate that the proposed kernels can outperform state-of-the-art graph kernels and deep learning models for graph classification.

In this work, we develop a new Quantum-based Matching Kernel (QBMK) for un-attributed graphs, by computing the kernel-based similarity between the quantum Shannon entropies of aligned vertices through the Continuous-time Quantum Walk (CTQW). The theoretical analysis reveals that the proposed QBMK kernel not only addresses the shortcoming of neglecting the structural correspondence information between graphs arising in existing R-convolution graph kernels, but also overcomes the problem of neglecting the structural differences between pairs of aligned vertices arising in existing vertex-based matching kernels. Moreover, the proposed QBMK kernel can simultaneously capture both global and local structural characteristics through the quantum Shannon entropies. Experimental evaluations on standard graph datasets demonstrate that the proposed QBMK kernel is able to outperform state-of-the-art graph kernels and graph deep learning approaches.

Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective structural characteristics for graph data analysis. To this end, during the encoding process, we commence by utilizing the hard node assignment to decompose a sample graph into a family of separated subgraphs. We compress each subgraph into a coarsened node, transforming the original graph into a coarsened graph. On the other hand, during the decoding process, we adopt the soft node assignment to reconstruct the original graph structure by expanding the coarsened nodes. By hierarchically performing the above compressing procedure during the decoding process as well as the expanding procedure during the decoding process, the proposed HC-GAE can effectively extract bidirectionally hierarchical structural features of the original sample graph. Furthermore, we re-design the loss function that can integrate the information from either the encoder or the decoder. Since the associated graph convolution operation of the proposed HC-GAE is restricted in each individual separated subgraph and cannot propagate the node information between different subgraphs, the proposed HC-GAE can significantly reduce the over-smoothing problem arising in the classical convolution-based GAEs. The proposed HC-GAE can generate effective representations for either node classification or graph classification, and the experiments demonstrate the effectiveness on real-world datasets.

Underwater images normally suffer from visual degradation issues such as color deviations, low contrasts, and blurred details. Recently, numerous underwater image enhancement algorithms have been proposed to address these issues. However, constrained by underwater conditions, acquiring non-underwater images and depth maps for underwater images is often challenging. This limitation significantly hampers the performance of data driven-based methods and physical model-based methods. Additionally, existing physical model-based methods typically require manual parameter settings, which tend to be bruteforce and insufficient to effectively address the diverse underwater scenes. To overcome these limitations, this paper presents a comprehensive underwater image enhancement framework comprising three phases: metamergence (i.e., meta submergence), metalief (i.e., meta relief), and metaebb (i.e., meta ebb). These phases are dedicated to virtual underwater image synthesis, underwater image depth map estimation, and the configuration of state-of-the-art physical models for underwater image enhancement by reinforcement learning, separately. While the three phases are trained separately, the former phase provides the necessary data for training the latter. We refer to the overall three phases as metalantis (i.e., meta Atlantis) because its training processes, involving variations from submergence via relief to ebb over indoor scenes, mimic the virtual variations of Atlantis. The metalantis framework empowers state-of-the-art physical models of underwater imaging through reinforcement learning with virtually generated data. The well-trained metalantis framework can take an underwater image as the sole input, process it into virtual representations, and finally enhance it. Comprehensive qualitative and quantitative empirical evaluations validate that our metalantis framework outperforms state-of-the-art underwater image enhancement methods. We release our code at https://gitee.com/wanghaoupc/Metalantis_UIE.

In this work, we propose two novel quantum walk kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), between un-attributed graph structures. Different from most classical graph kernels, the proposed HAQJSK kernels can incorporate hierarchical aligned structure information between graphs and transform graphs of random sizes into fixed-size aligned graph structures, i.e., the Hierarchical Transitive Aligned Adjacency Matrix of vertices and the Hierarchical Transitive Aligned Density Matrix of the Continuous-Time Quantum Walks (CTQW). With pairwise graphs to hand, the resulting HAQJSK kernels are defined by computing the Quantum Jensen-Shannon Divergence (QJSD) between their transitive aligned graph structures. We show that the proposed HAQJSK kernels not only reflect richer intrinsic whole graph characteristics in terms of the CTQW, but also address the drawback of neglecting structural correspondence information that arises in most R-convolution graph kernels. Moreover, unlike the previous QJSD based graph kernels associated with the QJSD and the CTQW, the proposed HAQJSK kernels can simultaneously guarantee the properties of permutation invariant and positive definiteness, explaining the theoretical advantages of the HAQJSK kernels. The experiment indicates the effectiveness of the new proposed kernels.

To ease the process of building Knowledge Graphs (KGs) from scratch, a cost-effective method is required to enrich a KG using the triples extracted from a corpus. However, it is challenging to enrich a KG with newly extracted triples since they contain noisy information. This paper proposes to refine a KG by leveraging information extracted from a corpus. In particular, we first formulate the task of building KGs as two coupled sub-tasks, namely join event extraction and knowledge graph fusion. We then propose a collaborative knowledge graph fusion framework, which is composed of an explorer and a supervisor, to allow the involved two sub-tasks to mutually assist each other in an alternative manner. More concretely, an explorer extracts triples from a corpus supervised by both the ground-truth annotation and the KG provided by the supervisor. Furthermore, a supervisor then evaluates the extracted triples and enriches the KG with those that are highly ranked. To implement this evaluation, we further propose a translated relation alignment scoring mechanism to align and translate the extracted triples to the KG. Experimental results verify that this collaboration can improve both the performance of our sub-tasks, and contribute to high-quality enriched knowledge graphs.

Graph convolutional networks (GCNs) are powerful tools for graph structure data analysis. One main drawback arising in most existing GCN models is that of the oversmoothing problem, i.e., the vertex features abstracted from the existing graph convolution operation have previously tended to be indistinguishable if the GCN model has many convolutional layers (e.g., more than two layers). To address this problem, in this article, we propose a family of aligned vertex convolutional network (AVCN) models that focus on learning multiscale features from local-level vertices for graph classification. This is done by adopting a transitive vertex alignment algorithm to transform arbitrary-sized graphs into fixed-size grid structures. Furthermore, we define a new aligned vertex convolution operation that can effectively learn multiscale vertex characteristics by gradually aggregating local-level neighboring aligned vertices residing on the original grid structures into a new packed aligned vertex. With the new vertex convolution operation to hand, we propose two architectures for the AVCN models to extract different hierarchical multiscale vertex feature representations for graph classification. We show that the proposed models can avoid iteratively propagating redundant information between specific neighboring vertices, restricting the notorious oversmoothing problem arising in most spatial-based GCN models. Experimental evaluations on benchmark datasets demonstrate the effectiveness.

With the explosive growth of online information, the significant application value of recommender systems has received considerable attention. Since user–item interactions can naturally fit into graph structure data , graph neural networks (GNNs), by virtue of their strong ability in graph representation learning , have become the new state-of-the-art approach to recommender systems. Recently, GNN-based contrastive self-supervised learning (SSL) methods have received careful attention due to their superiority over graph-based recommendation under the typical supervised learning paradigm . However, to achieve state-of-the-art performance, GNN-based recommendation with SSL often needs a huge amount of negative examples and the model’s performance is heavily dependent on complex data augmentations . Also, the information interaction among various augmented views is often performed under a single perspective (e.g., structure/feature space or node/graph level). In this paper, we propose a novel bootstrapped graph representation learning with local and global regularization for recommendation, i.e., BLoG, which constructs positive/negative pairs based on the aggregated node features by referring to two alternate views of the original user–item graph structure. In particular, BLoG learns user–item representations by encoding two augmented versions of a user–item bipartite graph using two separate encoders: an online encoder and a target encoder. To facilitate the information interaction between these two distinct graph encoders, we introduce local and global regularization for recommendation, where a graph structural contrastive loss and a node-level semantic loss are defined for local regularization while a graph-level contrastive loss is used for global regularization. An alternative optimization approach is used to train the online encoder and the target encoder. Experimental studies on three benchmark datasets demonstrate that BLoG achieves better recommendation accuracy than several existing baselines.

Pedestrians are often vulnerable users of urban roads and ensuring their safety is a pressing challenge in the filed of intelligent transportation. Multiple pedestrian tracking is one of the key technologies for traffic statistics and abnormal behavior analysis, etc. Detection-based tracking methods have achieved remarkable results and have become mainstream processing schemes. However, target association is still immature and less effective in complex scenarios. In the proposed tracking system, several candidates surrounding each detected pedestrian are selected sparsely, and the associating relationship between the target and these candidates is determined based on a graph attention map. These graph attention maps contain positional correlations of the matching pairs and are applicable with pedestrians’ posture variations. The weighted correlating value is estimated with the positional weighted matrix and merged attention map. The correlating relationship is confirmed with the weighted correlating value and distance matching loss. To enhance the computation efficiency of the graph attention maps for these tracked targets and candidates, feature extraction is processed separately. Convolutional features extracted from one specific middle layer of the backbone network are used to represent each target or candidate. The experiment results show that the proposed tracker achieves better performance than the other five state-of-the-art trackers on three publicly available databases.

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 alter the original spatial position 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 indicate the effectiveness of the proposed QSGCNN model in relation to existing state-of-the-art methods. Experiments on benchmark graph classification datasets demonstrate the effectiveness of the proposed QSGCNN model.

Network representations are powerful tools to modeling the dynamic time-varying financial complex systems consisting of multiple co-evolving financial time series, e.g., stock prices. In this work, we develop a novel framework to compute the kernel-based similarity measure between dynamic time-varying financial networks. Specifically, we explore whether the proposed kernel can be employed to understand the structural evolution of the financial networks with time associated with standard kernel machines. For a set of time-varying financial networks with each vertex representing the individual time series of a different stock and each edge between a pair of time series representing the absolute value of their Pearson correlation, our start point is to compute the commute time (CT) matrix associated with the weighted adjacency matrix of the network structures, where each element of the matrix can be seen as the enhanced correlation value between pairwise stocks. For each network, we show how the CT matrix allows us to identify a reliable set of dominant correlated time series as well as an associated dominant probability distribution of the stock belonging to this set. Furthermore, we represent each original network as a discrete dominant Shannon entropy time series computed from the dominant probability distribution. With the dominant entropy time series for each pair of financial networks to hand, we develop an entropic dynamic time warping kernels through the classical dynamic time warping framework, for analyzing the financial time-varying networks. We show that the proposed kernel bridges the gap between graph kernels and the classical dynamic time warping framework for multiple financial time series analysis. Experiments on time-varying networks extracted through New York Stock Exchange (NYSE) database demonstrate that the effectiveness of the proposed method.

The structure of networks can be efficiently represented using motifs, which are those subgraphs that recur most frequently. One route to understanding the motif structure of a network is to study the distribution of subgraphs using statistical mechanics. In this article, we address the use of motifs as network primitives using the cluster expansion from statistical physics. By mapping the network motifs to clusters in the gas model, we derive the partition function for a network, and this allows us to calculate global thermodynamic quantities, such as energy and entropy. We present analytical expressions for the number of certain types of motifs, and compute their associated entropy. We conduct numerical experiments for synthetic and real-world data sets and evaluate the qualitative and quantitative characterizations of the motif entropy derived from the partition function. We find that the motif entropy for real-world networks, such as financial stock market networks, is sensitive to the variance in network structure. This is in line with recent evidence that network motifs can be regarded as basic elements with well-defined information-processing functions.

This paper proposes a novel Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. The main idea is to define a new quantum-inspired spatial graph convolution associated with pre-transformed fixed-sized aligned grid structures of graphs, in terms of quantum information propagation between grid vertices of each graph. We show that the proposed QSGCNN model can significantly reduce either the information loss or the notorious tottering problem arising in existing spatially-based Graph Convolutional Network (GCN) models. Experiments on benchmark graph datasets demonstrate the effectiveness of the proposed QSGCNN model.

In this paper, we develop a new graph kernel, namely the Hierarchical Transitive-Aligned Kernel, by transitively aligning the vertices between graphs through a family of hierarchical prototype graphs. Comparing to most existing state-of-the-art graph kernels, the proposed kernel has three theoretical advantages. First, it incorporates the locational correspondence information between graphs into the kernel computation, and thus overcomes the shortcoming of ignoring structural correspondences arising in most R-convolution kernels. Second, it guarantees the transitivity between the correspondence information that is not available for most existing matching kernels. Third, it incorporates the information of all graphs under comparisons into the kernel computation process, and thus encapsulates richer characteristics. Experimental evaluations demonstrate the effectiveness of the new transitive-aligned kernel.

Graph Neural Networks (GNNs) have achieved state-of-the-art performance on a wide range of graph-based tasks such as graph classification and node classification. This is because the unique structure of GNNs allows them to effectively learn embeddings for unstructured data. One important operation for graph classification tasks is downsampling or pooling, which obtains graph representations from node representations. However, most GNNs are associated with global pooling, that can not learn hierarchical graph representations. Meanwhile, current hierarchical pooling methods have the shortcomings of unclear node assignment and uniform aggregation. To overcome these drawbacks, we propose an attention-based differentiable pooling operation in this paper, which can learn a hard cluster assignment for nodes and aggregate nodes in each cluster differently by introducing an attention mechanism. Experiments on standard graph classification benchmarks show that our proposed approach performs better when compared with other competing methods.

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.

Joint-event-extraction, which extracts structural information (i.e., entities or triggers of events) from unstructured real-world corpora, has attracted more and more research attention in natural language processing. Most existing works do not fully address the sparse co-occurrence relationships between entities and triggers, which loses this important information and thus deteriorates the extraction performance. To mitigate this issue, we first define the joint-event-extraction as a sequence-to-sequence labeling task with a tag set composed of tags of triggers and entities. Then, to incorporate the missing information in the aforementioned co-occurrence relationships, we propose a Cross-Supervised Mechanism (CSM) to alternately supervise the extraction of either triggers or entities based on the type distribution of each other. Moreover, since the connected entities and triggers naturally form a heterogeneous information network (HIN), we leverage the latent pattern along meta-paths for a given corpus to further improve the performance of our proposed method. To verify the effectiveness of our proposed method, we conduct extensive experiments on four real-world datasets as well as compare our method with state-of-the-art methods. Empirical results and analysis show that our approach outperforms the state-of- the-art methods in both entity and trigger extraction.

Network representations are powerful tools for the analysis of time-varying financial complex systems consisting of multiple co-evolving financial time series, e.g., stock prices, etc. In this work, we develop a new kernel-based similarity measure between dynamic time-varying financial networks. Our ideas is to transform each original financial network into quantum-based entropy time series and compute the similarity measure based on the classical dynamic time warping framework associated with the entropy time series. The proposed method bridges the gap between graph kernels and the classical dynamic time warping framework for multiple financial time series analysis. Experiments on time-varying networks abstracted from financial time series of New York Stock Exchange (NYSE) database demonstrate that our approach can effectively discriminate the abrupt structural changes in terms of the extreme financial events.

We develop a novel method for measuring the similarity between complete weighted graphs, which are probed by means of the discrete-time quantum walks. Directly probing complete graphs using discrete-time quantum walks is intractable due to the cost of simulating the quantum walk. We overcome this problem by extracting a commute time minimum spanning tree from the complete weighted graph. The spanning tree is probed by a discrete-time quantum walk which is initialized using a weighted version of the Perron-Frobenius operator. This naturally encapsulates the edge weight information for the spanning tree extracted from the original graph. For each pair of complete weighted graphs to be compared, we simulate a discrete-time quantum walk on each of the corresponding commute time minimum spanning trees and, then, compute the associated density matrices for the quantum walks. The probability of the walk visiting each edge of the spanning tree is given by the diagonal elements of the density matrices. The similarity between each pair of graphs is then computed using either: 1) the inner product or 2) the negative exponential of the Jensen-Shannon divergence between the probability distributions. We show that in both cases the resulting similarity measure is positive definite and, therefore, corresponds to a kernel on the graphs. We perform a series of experiments on publicly available graph datasets from a variety of different domains, together with time-varying financial networks extracted from data for the New York Stock Exchange. Our experiments demonstrate the effectiveness of the proposed similarity measures.

Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps people to gain more experience from mistakes and thus to perform better in similar future tasks. This paper investigates the counterfactual thinking for agents to find optimal decision-making strategies in multi-agent reinforcement learning environments. In particular, we propose a multi-agent deep reinforcement learning model with a structure which mimics the human-psychological counterfactual thinking process to improve the competitive abilities for agents. To this end, our model generates several possible actions (intent actions) with a parallel policy structure and estimates the rewards and regrets for these intent actions based on its current understanding of the environment. Our model incorporates a scenario-based framework to link the estimated regrets with its inner policies. During the iterations, our model updates the parallel policies and the corresponding scenario-based regrets for agents simultaneously. To verify the effectiveness of our proposed model, we conduct extensive experiments. Experimental results show that counterfactual thinking can actually benefit the agents to obtain more accumulative rewards from the environments with fair information by comparing to their opponents.

The financial contagion describes a widespread phenomenon of the interdependency for pairs of stock time series during the market abnormality periods. Since the interdependency rule between stocks varies in different periods, it is difficult to capture the interdependency rule for stocks related to the market status effectively. We define this interdependency rule as, the co-movement pattern, a high-dimensional co-varying relationship between pairs of stock time series and propose a Co-movement Attention Model (CAM) to discover the co-movement patterns for the stocks related to the market status. With the discovered patterns, CAM focuses on the stock-level abnormality periods by the co-movement attention automatically. CAM is trained under the supervision of the stock sector label information. CAM has the ability to model financial contagion and detect global market abnormality periods, by modeling co-movement patterns on every pair-wise stocks. We verify our methods on the real-world stock data and compare it with state of the art methods. The experimental result shows that our method not only captures the co-movement attentions with better quantitative metric values but also covers more real market abnormalities than the other alternatives.

In this paper, we develop a new deep hybrid graph kernel. This is based on the depth-based matching kernel [1] and the Weisfeiler-Lehman subtree kernel [2], by jointly computing a basic deep kernel that simultaneously captures the relationship between the combined kernels through deep learning networks. Specifically, for a set of graphs under investigations, we commence by computing two kernel matrices using each of the separate kernels. With the two kernel matrices to hand, for each graph we use the kernel value between the graph and each of the training graphs as the graph characterisation vector. This vector can be seen as a kernel-based similarity embedding vector of the graph [3]. We use the embedding vectors of all graphs to train a deep auto encoder network, that is optimized using Stochastic Gradient Descent together with the Deep Belief Network for pretraining. The deep representation computed through the deep learning network captures the main relationship between the depth-based matching kernel and the Weisfeiler-Lehman subtree kernel. The resulting deep hybrid graph kernel is computed by summing the original kernels together with the dot product kernel between their deep representations. We show that the deep hybrid graph kernel not only captures the joint information between the associated depth-based matching and Weisfeiler-Lehman subtree kernels, but also reflects the information content over all graphs under investigations. Experimental evaluations demonstrate the effectiveness of the proposed kernel.

This paper proposes a new graph convolutional neural architecture based on a depth-based representation of graph structure, called the depth-based subgraph convolutional neural networks (DS-CNNs), which integrates both the global topological and local connectivity structures within a graph. Our idea is to decompose a graph into a family of$K$-layer expansion subgraphs rooted at each vertex, and then a set of convolution filters are designed over these subgraphs to capture local connectivity structural information. Specifically, we commence by establishing a family of$K$-layer expansion subgraphs for each vertex of graph by mapping graph to tree procedures, which can provide global topological arrangement information contained within a graph. We then design a set of fixed-size convolution filters and integrate them with these subgraphs (depicted in Figure 1). The idea is to apply convolution filters sliding over the entire subgraphs of a vertex to extract the local features analogous to the standard convolution operation on grid data. In particular, the convolution operation captures the local structural information within the graph, and has the weight sharing property among different positions of subgraph; the pooling operation acts directly on the output of the preceding layer without any preprocessing scheme (e.g., clustering or other techniques). Experiments on three graph-structured datasets demonstrate that our model DS-CNNs are able to outperform six state-of-the-art methods at the task of node classification.

In this work we propose a novel and compact Neighbor Reconstruction Method (NRM) which is a unified pre-processing method for graph-based sparse spectral algorithms. This method is conducted by vector operations on a central point and its corresponding neighbor points. NRM generates new neighbor points which can capture the local space structure of the central point more appropriately than original neighbor points. With NRM, a large number of sparse spectral based nonlinear feature extraction and selection algorithms gain significant improvement. Specifically, we embedded NRM to several classical algorithms, Local Linear Embedding (LLE) [1], Laplacian Eigenmaps (LE) [2] and Unsupervised Feature Selection for Multi-cluster Data (MCFS) [3], with accuracy improvement of up to 7%, 2.6%, 2.4% on ORL, CIFAR 10, and MINST data sets respectively. We also apply NRM to a Super Resolution algorithm, A+ [5], and obtain 0.12dB improvement than original method.

K-means algorithm has been widely used in machine learning and data mining due to its simplicity and good performance. However, the standard k-means algorithm would be quite slow for clustering millions of data into thousands of or even tens of thousands of clusters. In this paper, we propose a fast k-means algorithm named multi-stage k-means (MKM) which uses a multi-stage filtering approach. The multi-stage filtering approach greatly accelerates the k-means algorithm via a coarse-to-fine search strategy. To further speed up the algorithm, hashing is introduced to accelerate the assignment step which is the most time-consuming part in k-means. Extensive experiments on several massive datasets show that the proposed algorithm can obtain up to 600X speed-up over the k-means algorithm with comparable accuracy.

In this paper, we develop a new transitive aligned Weisfeiler-Lehman subtree kernel. This kernel not only overcomes the shortcoming of ignoring correspondence information between isomorphic substructures that arises in existing R-convolution kernels, but also guarantees the transitivity between the correspondence information that is not available for existing matching kernels. Our kernel outperforms state-of-the-art graph kernels in terms of classification accuracy on standard graph datasets.

In this paper, we propose a novel entropic signature for graphs, where we probe the graphs by means of continuous-time quantum walks. More precisely, we characterise the structure of a graph through its average mixing matrix. The average mixing matrix is a doubly-stochastic matrix that encapsulates the time-averaged behaviour of a continuous-time quantum walk on the graph, i.e., the ij-th element of the average mixing matrix represents the time-averaged transition probability of a continuous-time quantum walk from the vertex vito the vertex vj. With this matrix to hand, we can associate a probability distribution with each vertex of the graph. We define a novel entropic signature by concatenating the average Shannon entropy of these probability distributions with their Jensen-Shannon divergence. We show that this new entropic measure can encaspulate the rich structural information of the graphs, thus allowing to discriminate between different structures. We explore the proposed entropic measure on several graph datasets abstracted from bioinformatics databases and we compare it with alternative entropic signatures in the literature. The experimental results demonstrate the effectiveness and efficiency of our method.

Bai and Hancock recently proposed a novel edge-based matching kernel for graphs [1], by aligning depth-based representations. Unfortunately, one drawback arising in their kernel is the computational inefficiency for large graphs. This follows the fact that their kernel is essentially defined on directed line graphs. Moreover, the computational complexity of the kernel is cubic in the vertex number of the line graph. Since the directed line graph is a dual representation and each vertex represents a directed arc residing on the edge of the original graph. For a graph having n vertices, there may be at most n(n − 1) directed arcs residing on the edges and thus at most n(n − 1) vertices in the directed line graph. As a result, computing the kernel through the line graphs may require time complexity O(n6) for the worst case, making the kernel unapplicable for graphs having hundreds of vertices. The aim of this paper is to overcome this inefficiency, by proposing a new edge-based matching kernel. In order to cope with large graph structures, we propose to construct a sparser version of the original graph using the simplification method introduced in [2]. More specifically, we compute the minimum spanning tree over the commute time matrix of a graph. This spanning tree representation minimizes the number of edges of the original graph while preserving most of its structural information. With this simplification method to hand, the new edge-based matching kernel between two graphs is then computed on the directed line graphs transformed from their respective minimum spanning trees. We show that this strategy significantly reduces the computational complexity to O(n3). We evaluate the performance of the proposed kernels on several standard graph datasets. The experimental results demonstrate the effectiveness and efficiency.

Graph kernels are powerful tools for structural analysis in computer vision.Unfortunately, most existing stateof-the-art graph kernels ignore the locational or structural correspondence information between graphs, based on the visual background.This drawback influences the performance of existing kernels for computer vision based classification problems, e.g., classification of shapes, point clouds and digital images.The aim of this paper is to address the problem with existing kernels, by developing a novel vertex clustering graph kernel.We show that this kernel not only overcomes the shortcoming of ignoring correspondence information between isomorphic substructures that arises in most existing graph kernels, but also guarantees the transitivity between the correspondence information.Our kernel can easily outperform state-of-the-art graph kernels in terms of classification accuracy on standard shape based graph datasets.

The link prediction is a classical problem for computer science and many other research fields. Existing link prediction methods mainly apply the link patterns for the network in order to predict future possible links. However, in a network generated by the human interaction, the links may not only relate to the observed datasets, but also are affected by the decisions of human. That is to say, this kind of networks are affected by the game processes between all the related individuals. This paper proposes a model based on the dynamic network formation to mimic the game processes, and uses this model to deal with the link prediction problem. Moreover, we theoretically demonstrate the relationship between the parameters and the limit status of our model. Experimental results illustrate that the proposed model does better link prediction on the networks generated by human interaction than the traditional methods. Further more, this model gives a good prediction for the future possible links in a continuous time period.

We present a novel band weighting strategy that exploits multiple binary support vector machines (SVMs) to maximize interclass spectral distances for multiclass hyperspectral remote image classification. Specifically, we commence by training binary SVMs based on the original training samples. We then balance the bands of training samples by maximizing the modified classification scores for SVMs. This balance scheme enlarges the distances between individual training samples and the SVM hyperplane. For each class, we reformulate the binary SVM objective function based on the balanced training samples, resulting in a weighting vector that associates a weight to each spectral band for the class. For a testing sample, we weight it and then classify it by using the binary SVM, both with respect to every individual class. The classification result is obtained from the classifier with the greatest score. Experiments on two benchmark data sets show the effectiveness of the proposed strategy.

In this paper, we develop a new entropic matching kernel for weighted graphs by aligning depth-based representations. We demonstrate that this kernel can be seen as an \textbfaligned subtree kernel that incorporates explicit subtree correspondences, and thus addresses the drawback of neglecting the relative locations between substructures that arises in the R-convolution kernels. Experiments on standard datasets demonstrate that our kernel can easily outperform state-of-the-art graph kernels in terms of classification accuracy.

In information retrieval, efficient accomplishing the nearest neighbor search on large scale database is a great challenge. Hashing based indexing methods represent each data instance as a binary string to retrieve the approximate nearest neighbors. In this paper, we present a semi-randomized hashing approach to preserve the Euclidean distance by binary codes. Euclidean distance preserving is a classic research problem in hashing. Most hashing methods used purely randomized or optimized learning strategy to achieve this goal. Our method, on the other hand, combines both randomized and optimized strategies. It starts from generating multiple random vectors, and then approximates them by a single projection vector. In the quantization step, it uses the orthogonal transformation to minimize an upper bound of the deviation between real-valued vectors and binary codes. The proposed method overcomes the problem that randomized hash functions are isolated from the data distribution. What's more, our method supports an arbitrary number of hash functions, which is beneficial in building better hashing methods. The experiments show that our approach outperforms the alternative state-of-the-art methods for retrieval on the large scale dataset.

Bai and Hancock recently proposed a novel information theoretic kernel for graphs, namely the Jensen-Shannon graph kernel. One drawback of their approach is that it cannot be applied to either attributed or labeled graphs. In this paper, we aim to define a new Jensen-Shannon diffusion kernel for attributed graphs. We commence by using a tree-index based label strengthening method on an attributed graph with the objection of strengthening the vertex labels. We compute a label entropy to measure the uncertainty of the strengthened labels. With the required label entropies for a pair of graphs to hand, a new kernel for the pair of graphs can be defined by measuring the Jensen-Shannon divergence between the entropies. As the strengthened label of a vertex corresponds to a sub tree rooted at the vertex, the label entropy of a graph is determined by all sub trees identified by the tree-index algorithm. As a result, unlike most existing graph kernels in the literature which merely enumerate pairs of isomorphic substructures, our method incorporates all the identified sub trees into the computation of the kernel. The new kernel thus overcomes the shortcoming of discarding substructures having no corresponding isomorphic substructures. We explore our kernel on several graph datasets abstracted from bioinformatics databases.

In this paper, we aim to characterize hyper graphs in terms of structural complexities. To measure the complexity of a hyper graph in a straightforward way, we transform a hyper graph into a line graph which accurately reflects the multiple relationships exhibited by the hyper graph. To locate the dominant substructure within a line graph, we identify a centroid vertex by computing the minimum variance of its shortest path lengths. A family of directed centroid expansion sub graphs of the line graph is then derived from the centroid vertex. We compute the directed depth-based complexity trace of a hyper graph by measuring directed entropies on its directed sub graphs. The novel hyper graph complexity trace provides a flexible framework that can be applied to both hyper graphs and graphs. Experiments on standard (hyper)graph datasets demonstrate the effectiveness and efficiency of the new complexity trace.

In this paper, we present a hyper graph kernel computed using substructure isomorphism tests. Measuring the isomorphisms between hyper graphs straightforwardly tends to be elusive since a hyper graph may exhibit varying relational orders. We thus transform a hyper graph into a directed line graph. This not only accurately reflects the multiple relationships exhibited by the hyper graph but is also easier to manipulate isomorphism tests. To locate the isomorphisms between hyper graphs through their directed line graphs, we propose a new directed Weisfeiler-Lehman isomorphism test for directed graphs. The new isomorphism test precisely reflects the structure of the directed edges. By identifying the isomorphic substructures of directed graphs, the hyper graph kernel for a pair of hyper graphs is computed by counting the number of pair wise isomorphic substructures from their directed line graphs. We show that our kernel limits tottering that arises in the existing walk and sub tree based (hyper)graph kernels. Experiments on challenging (hyper)graph datasets demonstrate the effectiveness of our kernel.