Advanced Graph Neural Networks

Derniers papiers

• FOS: A Large-Scale Temporal Graph Benchmark for Scientific Interdisciplinary Link Prediction

  Kiyan Rezaee, Morteza Ziabakhsh, Niloofar Nikfarjam, Mohammad M. Ghassemi, Yazdan Rezaee Jouryabi, Sadegh Eskandari, Reza Lashgari · 25 novembre 2025

  Interdisciplinary scientific breakthroughs mostly emerge unexpectedly, and forecasting the formation of novel research fields remains a major challenge. We introduce FOS (Future Of Science), a comprehensive time-aware graph-based benchmark that reconstructs annual co-occurrence graphs of 65,027 rese…

• Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs

  Renchu Guan, Xuyang Li, Yachao Zhang, Wei Pang, Fausto Giunchiglia, Ximing Li, Yonghao Liu, Xiaoyue Feng · 25 novembre 2025

  Hypergraphs, as a generalization of traditional graphs, naturally capture high-order relationships. In recent years, hypergraph neural networks (HNNs) have been widely used to capture complex high-order relationships. However, most existing hypergraph neural network methods inherently rely on the ho…

• Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning

  Bo Jiang, Weijun Zhao, Beibei Wang, Xiao Wang, Jin Tang · 25 novembre 2025

  Recently, fine-tuning large-scale pre-trained GNNs has yielded remarkable attention in adapting pre-trained GNN models for downstream graph learning tasks. One representative fine-tuning method is to exploit adapter (termed AdapterGNN) which aims to 'augment' the pre-trained model by inserting a lig…

• Interpreting Graph Inference with Skyline Explanations

  Dazhuo Qiu, Haolai Che, Arijit Khan, Yinghui Wu · 25 novembre 2025

  Inference queries have been routinely issued to graph machine learning models such as graph neural networks (GNNs) for various network analytical tasks. Nevertheless, GNN outputs are often hard to interpret comprehensively. Existing methods typically conform to individual pre-defined explainability …

• Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems

  Yoshihiro Maruyama · 25 novembre 2025

  We develop a theory of category-equivariant neural networks (CENNs) that unifies group/groupoid-equivariant networks, poset/lattice-equivariant networks, graph and sheaf neural networks. Equivariance is formulated as naturality in a topological category with Radon measures, formulating linear and no…

• Generative Myopia: Why Diffusion Models Fail at Structure

  Milad Siami · 25 novembre 2025

  Graph Diffusion Models (GDMs) optimize for statistical likelihood, implicitly acting as \textbf{frequency filters} that favor abundant substructures over spectrally critical ones. We term this phenomenon \textbf{Generative Myopia}. In combinatorial tasks like graph sparsification, this leads to the …

• Investigating Representation Universality: Case Study on Genealogical Representations

  David D. Baek, Yuxiao Li, Max Tegmark · 25 novembre 2025

  Motivated by interpretability and reliability, we investigate whether large language models (LLMs) deploy universal geometric structures to encode discrete, graph-structured knowledge. To this end, we present two complementary experimental evidence that might support universality of graph representa…

• GraphMind: Theorem Selection and Conclusion Generation Framework with Dynamic GNN for LLM Reasoning

  Yutong Li, Yitian Zhou, Xudong Wang, GuoChen, Caiyan Qin · 25 novembre 2025

  Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, including multi-step reasoning such as mathematical proving. However, existing approaches often lack an explicit and dynamic mechanism to structurally represent and evolve interme…

• Learning to Compress Graphs via Dual Agents for Consistent Topological Robustness Evaluation

  Qisen Chai, Yansong Wang, Junjie Huang, Tao Jia · 25 novembre 2025

  As graph-structured data grow increasingly large, evaluating their robustness under adversarial attacks becomes computationally expensive and difficult to scale. To address this challenge, we propose to compress graphs into compact representations that preserve both topological structure and robustn…

• Node Embeddings via Neighbor Embeddings

  Jan Niklas B\"ohm, Marius Keute, Alica Guzm\'an, Sebastian Damrich, Andrew Draganov, Dmitry Kobak · 25 novembre 2025

  Node embeddings are a paradigm in non-parametric graph representation learning, where graph nodes are embedded into a given vector space to enable downstream processing. State-of-the-art node-embedding algorithms, such as DeepWalk and node2vec, are based on random-walk notions of node similarity and…

• Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings

  Zimo Yan, Zheng Xie, Chang Liu, Yuan Wang · 25 novembre 2025

  Message passing graph neural networks are widely used for learning on graphs, yet their expressive power is limited by the one-dimensional Weisfeiler-Lehman test and can fail to distinguish structurally different nodes. We provide rigorous theory for a Laplacian positional encoding that is invariant…

• Pre-training Graph Neural Networks on 2D and 3D Molecular Structures by using Multi-View Conditional Information Bottleneck

  Van Thuy Hoang, O-Joun Lee · 25 novembre 2025

  Recent pre-training strategies for molecular graphs have attempted to use 2D and 3D molecular views as both inputs and self-supervised signals, primarily aligning graph-level representations. However, existing studies remain limited in addressing two main challenges of multi-view molecular learning:…

• Graph Neural Networks vs Convolutional Neural Networks for Graph Domination Number Prediction

  Randy Davila, Beyzanur Ispir · 25 novembre 2025

  We investigate machine learning approaches to approximating the \emph{domination number} of graphs, the minimum size of a dominating set. Exact computation of this parameter is NP-hard, restricting classical methods to small instances. We compare two neural paradigms: Convolutional Neural Networks (…

• Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks

  Jiayi Luo, Qingyun Sun, Yuecen Wei, Haonan Yuan, Xingcheng Fu, Jianxin Li · 25 novembre 2025

  Multi-domain graph pre-training has emerged as a pivotal technique in developing graph foundation models. While it greatly improves the generalization of graph neural networks, its privacy risks under membership inference attacks (MIAs), which aim to identify whether a specific instance was used in …

• Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models

  Jiayi Luo, Qingyun Sun, Lingjuan Lyu, Ziwei Zhang, Haonan Yuan, Xingcheng Fu, Jianxin Li · 25 novembre 2025

  Graph Foundation Models (GFMs) are pre-trained on diverse source domains and adapted to unseen targets, enabling broad generalization for graph machine learning. Despite that GFMs have attracted considerable attention recently, their vulnerability to backdoor attacks remains largely underexplored. A…

• Towards Efficient LLM-aware Heterogeneous Graph Learning

  Wenda Li, Tongya Zheng, Shunyu Liu, Yu Wang, Kaixuan Chen, Hanyang Yuan, Bingde Hu, Zujie Ren, Mingli Song, Gang Chen · 25 novembre 2025

  Heterogeneous graphs are widely present in real-world complex networks, where the diversity of node and relation types leads to complex and rich semantics. Efforts for modeling complex relation semantics in heterogeneous graphs are restricted by the limitations of predefined semantic dependencies an…

• Ternary Gamma Semirings as a Novel Algebraic Framework for Learnable Symbolic Reasoning

  Chandrasekhar Gokavarapu (Department of Mathematics, Government College), D. Madhusudhana Rao (Department of Mathematics, Government College for Women) · 25 novembre 2025

  Binary semirings such as the tropical, log, and probability semirings form a core algebraic tool in classical and modern neural inference systems, supporting tasks like Viterbi decoding, dynamic programming, and probabilistic reasoning. However, these structures rely on a binary multiplication opera…

• Model-to-Model Knowledge Transmission (M2KT): A Data-Free Framework for Cross-Model Understanding Transfer

  Pratham Sorte · 25 novembre 2025

  Modern artificial intelligence systems depend heavily on large datasets for both training and transferring knowledge between models. Knowledge distillation, transfer learning, and dataset distillation have made such transfers more efficient, yet they remain fundamentally data-driven: a teacher must …

• LLM-Powered Text-Attributed Graph Anomaly Detection via Retrieval-Augmented Reasoning

  Haoyan Xu, Ruizhi Qian, Zhengtao Yao, Ziyi Liu, Li Li, Yuqi Li, Yanshu Li, Wenqing Zheng, Daniele Rosa, Daniel Barcklow, Senthil Kumar, Jieyu Zhao, Yue Zhao · 25 novembre 2025

  Anomaly detection on attributed graphs plays an essential role in applications such as fraud detection, intrusion monitoring, and misinformation analysis. However, text-attributed graphs (TAGs), in which node information is expressed in natural language, remain underexplored, largely due to the abse…

• KGpipe: Generation and Evaluation of Pipelines for Data Integration into Knowledge Graphs

  Marvin Hofer, Erhard Rahm · 25 novembre 2025

  Building high-quality knowledge graphs (KGs) from diverse sources requires combining methods for information extraction, data transformation, ontology mapping, entity matching, and data fusion. Numerous methods and tools exist for each of these tasks, but support for combining them into reproducible…

• HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representations

  Cao Linxiao, Wang Ruitao, Li Jindong, Zhou Zhipeng, Yang Menglin · 25 novembre 2025

  Retrieval-augmented generation (RAG) enables large language models (LLMs) to access external knowledge, helping mitigate hallucinations and enhance domain-specific expertise. Graph-based RAG enhances structural reasoning by introducing explicit relational organization that enables information propag…

• When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected

  Haotian Xu, Yuning You, Tengfei Ma · 24 novembre 2025

  Graphs provide a unified representation of semantic content and relational structure, making them a natural fit for domains such as molecular modeling, citation networks, and social graphs. Meanwhile, large language models (LLMs) have excelled at understanding natural language and integrating cross-…

• GCL-OT: Graph Contrastive Learning with Optimal Transport for Heterophilic Text-Attributed Graphs

  Yating Ren, Yikun Ban, Huobin Tan · 24 novembre 2025

  Recently, structure-text contrastive learning has shown promising performance on text-attributed graphs by leveraging the complementary strengths of graph neural networks and language models. However, existing methods typically rely on homophily assumptions in similarity estimation and hard optimiza…

• Topologic Attention Networks: Attending to Direct and Indirect Neighbors through Gaussian Belief Propagation

  Marshall Rosenhoover, Huaming Zhang · 24 novembre 2025

  Graph Neural Networks rely on local message passing, which limits their ability to model long-range dependencies in graphs. Existing approaches extend this range through continuous-time dynamics or dense self-attention, but both suffer from high computational cost and limited scalability. We propose…

• PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling

  Zhongjie Dai, Tao Feng, Jiaxuan You · 24 novembre 2025

  The growing number of Large Language Models (LLMs) with diverse capabilities and response styles provides users with a wider range of choices, which presents challenges in selecting appropriate LLMs, as user preferences vary in terms of performance, cost, and response style. Current LLM selection me…