Advanced Graph Neural Networks

Derniers papiers

• SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data

  Andrea Zerio, Maya Bechler-Speicher, Maor Huri, Marie Vibeke Vestergaard, Ran Gilad-Bachrach, Tine Jess, Samir Bhatt, Aleksejs Sazonovs · 24 février 2026

  Real-world temporal data often consists of multiple signal types recorded at irregular, asynchronous intervals. For instance, in the medical domain, different types of blood tests can be measured at different times and frequencies, resulting in fragmented and unevenly scattered temporal data. Simila…

• Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering

  Sen Zhao, Lincheng Zhou, Yue Chen, Ding Zou · 24 février 2026

  Retrieval-Augmented Generation (RAG) enhances the reasoning ability of Large Language Models (LLMs) by dynamically integrating external knowledge, thereby mitigating hallucinations and strengthening contextual grounding for structured data such as graphs. Nevertheless, most existing RAG variants for…

• Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space

  Xin He, Yili Wang, Wenqi Fan, Xu Shen, Xin Juan, Rui Miao, Xin Wang · 24 février 2026

  Graph Neural Networks (GNNs) have shown great success in various graph-based learning tasks. However, it often faces the issue of over-smoothing as the model depth increases, which causes all node representations to converge to a single value and become indistinguishable. This issue stems from the i…

• GraphOmni: A Comprehensive and Extensible Benchmark Framework for Large Language Models on Graph-theoretic Tasks

  Hao Xu, Xiangru Jian, Xinjian Zhao, Wei Pang, Chao Zhang, Suyuchen Wang, Qixin Zhang, Zhengyuan Dong, Joao Monteiro, Bang Liu, Qiuzhuang Sun, Tianshu Yu · 24 février 2026

  This paper introduces GraphOmni, a comprehensive benchmark designed to evaluate the reasoning capabilities of LLMs on graph-theoretic tasks articulated in natural language. GraphOmni encompasses diverse graph types, serialization formats, and prompting schemes, significantly exceeding prior efforts …

• Routing-Aware Explanations for Mixture of Experts Graph Models in Malware Detection

  Hossein Shokouhinejad, Roozbeh Razavi-Far, Griffin Higgins, Ali. A Ghorbani · 24 février 2026

  Mixture-of-Experts (MoE) offers flexible graph reasoning by combining multiple views of a graph through a learned router. We investigate routing-aware explanations for MoE graph models in malware detection using control flow graphs (CFGs). Our architecture builds diversity at two levels. At the node…

• Revisiting Graph Neural Networks for Graph-level Tasks: Taxonomy, Empirical Study, and Future Directions

  Haoyang Li, Yuming Xu, Alexander Zhou, Yongqi Zhang · 24 février 2026

  Graphs are fundamental data structures for modeling complex interactions in domains such as social networks, molecular structures, and biological systems. Graph-level tasks, which involve predicting properties or labels for entire graphs, are crucial for applications like molecular property predicti…

• Towards A Universal Graph Structural Encoder

  Jialin Chen, Haolan Zuo, Haoyu Peter Wang, Siqi Miao, Pan Li, Rex Ying · 24 février 2026

  Recent advancements in large-scale pre-training have shown the potential to learn generalizable representations for downstream tasks. In the graph domain, however, capturing and transferring structural information across different graph domains remains challenging, primarily due to the inherent diff…

• Nazrin: Atomic Tactics for Graph Neural Networks for Theorem Proving in Lean 4

  Leni Aniva, Iori Oikawa, David Dill, Clark Barrett · 24 février 2026

  In Machine-Assisted Theorem Proving, a theorem proving agent searches for a sequence of expressions and tactics that can prove a conjecture in a proof assistant. In this work, we introduce several novel concepts and capabilities to address obstacles faced by machine-assisted theorem proving. We fi…

• L2G-Net: Local to Global Spectral Graph Neural Networks via Cauchy Factorizations

  Samuel Fern\'andez-Mendui\~na, Eduardo Pavez, Antonio Ortega · 24 février 2026

  Despite their theoretical advantages, spectral methods based on the graph Fourier transform (GFT) are seldom used in graph neural networks (GNNs) due to the cost of computing the eigenbasis and the lack of vertex-domain locality in spectral representations. As a result, most GNNs rely on local appro…

• From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection

  Yixin Liu, Shiyuan Li, Yu Zheng, Qingfeng Chen, Chengqi Zhang, Philip S. Yu, Shirui Pan · 24 février 2026

  Graph anomaly detection (GAD) is critical for identifying abnormal nodes in graph-structured data from diverse domains, including cybersecurity and social networks. The existing GAD methods often focus on the learning paradigms of "one-model-for-one-dataset", requiring dataset-specific training for …

• Spiking Graph Predictive Coding for Reliable OOD Generalization

  Jing Ren, Jiapeng Du, Bowen Li, Ziqi Xu, Xin Zheng, Hong Jia, Suyu Ma, Xiwei Xu, Feng Xia · 24 février 2026

  Graphs provide a powerful basis for modeling Web-based relational data, with expressive GNNs to support the effective learning in dynamic web environments. However, real-world deployment is hindered by pervasive out-of-distribution (OOD) shifts, where evolving user activity and changing content sema…

• Grokking Finite-Dimensional Algebra

  Pascal Jr Tikeng Notsawo, Guillaume Dumas, Guillaume Rabusseau · 24 février 2026

  This paper investigates the grokking phenomenon, which refers to the sudden transition from a long memorization to generalization observed during neural networks training, in the context of learning multiplication in finite-dimensional algebras (FDA). While prior work on grokking has focused mainly …

• Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision

  Yuxing Tian, Yiyan Qi, Fengran Mo, Weixu Zhang, Jian Guo, Jian-Yun Nie · 24 février 2026

  Dynamic graph anomaly detection (DGAD) is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies. Existing methods are either unsupervised or semi-supervised: unsupervised methods avoid the need for labeled anomalies but often produce ambiguous bou…

• Revisiting Node Affinity Prediction in Temporal Graphs

  Or Feldman, Krishna Sri Ipsit Mantri, Moshe Eliasof, Chaim Baskin · 24 février 2026

  Node affinity prediction is a common task that is widely used in temporal graph learning with applications in social and financial networks, recommender systems, and more. Recent works have addressed this task by adapting state-of-the-art dynamic link property prediction models to node affinity pred…

• Training-Free Cross-Architecture Merging for Graph Neural Networks

  Rishabh Bhattacharya, Vikaskumar Kalsariya, Naresh Manwani · 24 février 2026

  Model merging has emerged as a powerful paradigm for combining the capabilities of distinct expert models without the high computational cost of retraining, yet current methods are fundamentally constrained to homogeneous architectures. For GNNs, however, message passing is topology-dependent and se…

• DGPO: RL-Steered Graph Diffusion for Neural Architecture Generation

  Aleksei Liuliakov, Luca Hermes, Barbara Hammer · 24 février 2026

  Reinforcement learning fine-tuning has proven effective for steering generative diffusion models toward desired properties in image and molecular domains. Graph diffusion models have similarly been applied to combinatorial structure generation, including neural architecture search (NAS). However, ne…

• VecFormer: Towards Efficient and Generalizable Graph Transformer with Graph Token Attention

  Jingbo Zhou, Jun Xia, Siyuan Li, Yunfan Liu, Wenjun Wang, Yufei Huang, Changxi Chi, Mutian Hong, Zhuoli Ouyang, Shu Wang, Zhongqi Wang, Xingyu Wu, Chang Yu, Stan Z. Li · 24 février 2026

  Graph Transformer has demonstrated impressive capabilities in the field of graph representation learning. However, existing approaches face two critical challenges: (1) most models suffer from exponentially increasing computational complexity, making it difficult to scale to large graphs; (2) attent…

• RKHS Representation of Algebraic Convolutional Filters with Integral Operators

  Alejandro Parada-Mayorga, Alejandro Ribeiro, Juan Bazerque · 24 février 2026

  Integral operators play a central role in signal processing, underpinning classical convolution, and filtering on continuous network models such as graphons. While these operators are traditionally analyzed through spectral decompositions, their connection to reproducing kernel Hilbert spaces (RKHS)…

• HEHRGNN: A Unified Embedding Model for Knowledge Graphs with Hyperedges and Hyper-Relational Edges

  Rajesh Rajagopalamenon, Unnikrishnan Cheramangalath · 24 février 2026

  Knowledge Graph(KG) has gained traction as a machine-readable organization of real-world knowledge for analytics using artificial intelligence systems. Graph Neural Network(GNN), is proven to be an effective KG embedding technique that enables various downstream tasks like link prediction, node clas…

• Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks

  Yijiashun Qi, Hanzhe Guo, Yijiazhen Qi · 24 février 2026

  Small and Medium Enterprises (SMEs) constitute 99.9% of U.S. businesses and generate 44% of economic activity, yet systematically identifying high-potential SMEs remains an open challenge. We introduce SME-HGT, a Heterogeneous Graph Transformer framework that predicts which SBIR Phase I awardees wil…

• Temporal-Aware Heterogeneous Graph Reasoning with Multi-View Fusion for Temporal Question Answering

  Wuzhenghong Wen, Bowen Zhou, Jinwen Huang, Xianjie Wu, Yuwei Sun, Su Pan, Liang Li, Jianting Liu · 24 février 2026

  Question Answering over Temporal Knowledge Graphs (TKGQA) has attracted growing interest for handling time-sensitive queries. However, existing methods still struggle with: 1) weak incorporation of temporal constraints in question representation, causing biased reasoning; 2) limited ability to perfo…

• Optimizing Graph Causal Classification Models: Estimating Causal Effects and Addressing Confounders

  Simi Job, Xiaohui Tao, Taotao Cai, Haoran Xie, Jianming Yong, Xin Wang · 23 février 2026

  Graph data is becoming increasingly prevalent due to the growing demand for relational insights in AI across various domains. Organizations regularly use graph data to solve complex problems involving relationships and connections. Causal learning is especially important in this context, since it he…

• JPmHC Dynamical Isometry via Orthogonal Hyper-Connections

  Biswa Sengupta, Jinhua Wang, Leo Brunswic · 23 février 2026

  Recent advances in deep learning, exemplified by Hyper-Connections (HC), have expanded the residual connection paradigm by introducing wider residual streams and diverse connectivity patterns. While these innovations yield significant performance gains, they compromise the identity mapping property …

• Balancing Symmetry and Efficiency in Graph Flow Matching

  Benjamin Honor\'e, Alba Carballo-Castro, Yiming Qin, Pascal Frossard · 23 février 2026

  Equivariance is central to graph generative models, as it ensures the model respects the permutation symmetry of graphs. However, strict equivariance can increase computational cost due to added architectural constraints, and can slow down convergence because the model must be consistent across a la…

• COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models

  Jiajun Shen, Yufei Jin, Yi He, xingquan Zhu · 23 février 2026

  State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than modern alternatives, such as transformers. Advancing SMMs to graph structured data, especially for large graphs, is a significant challenge because SSMs …