Advanced Graph Neural Networks

Derniers papiers

• CCMamba: Selective State-Space Models for Higher-Order Graph Learning on Combinatorial Complexes

  Jiawen Chen, Qi Shao, Mingtong Zhou, Duxin Chen, Wenwu Yu · 29 janvier 2026

  Topological deep learning has emerged for modeling higher-order relational structures beyond pairwise interactions that standard graph neural networks fail to capture. Although combinatorial complexes offer a unified topological framework, most existing topological deep learning methods rely on loca…

• Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs

  Melika Mobini, Vincent Holst, Floriano Tori, Andres Algaba, Vincent Ginis · 29 janvier 2026

  Large language models are increasingly used to curate bibliographies, raising the question: are their reference lists distinguishable from human ones? We build paired citation graphs, ground truth and GPT-4o-generated (from parametric knowledge), for 10,000 focal papers ($\approx$ 275k references) f…

• GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus

  Zhaolin Hu, Kun Li, Hehe Fan, Yi Yang · 29 janvier 2026

  Linear attention mechanisms have emerged as efficient alternatives to full self-attention in Graph Transformers, offering linear time complexity. However, existing linear attention models often suffer from a significant drop in expressiveness due to low-rank projection structures and overly uniform …

• DiagLink: A Dual-User Diagnostic Assistance System by Synergizing Experts with LLMs and Knowledge Graphs

  Zihan Zhou, Yinan Liu, Yuyang Xie, Bin Wang, Xiaochun Yang, Zezheng Feng · 29 janvier 2026

  The global shortage and uneven distribution of medical expertise continue to hinder equitable access to accurate diagnostic care. While existing intelligent diagnostic system have shown promise, most struggle with dual-user interaction, and dynamic knowledge integration -- limiting their real-world …

• CASTER: Breaking the Cost-Performance Barrier in Multi-Agent Orchestration via Context-Aware Strategy for Task Efficient Routing

  Shanyv Liu, Xuyang Yuan, Tao Chen, Zijun Zhan, Zhu Han, Danyang Zheng, Weishan Zhang, Shaohua Cao · 28 janvier 2026

  Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware Strategy for Task Efficient Routing), a lightweight router for …

• Exploring Graph Learning Tasks with Pure LLMs: A Comprehensive Benchmark and Investigation

  Yuxiang Wang, Xinnan Dai, Wenqi Fan, Yao Ma · 28 janvier 2026

  In recent years, large language models (LLMs) have emerged as promising candidates for graph tasks. Many studies leverage natural language to describe graphs and apply LLMs for reasoning, yet most focus narrowly on performance benchmarks without fully comparing LLMs to graph learning models or explo…

• The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning

  Ren Zhuang, Ben Wang, Shuifa Sun · 28 janvier 2026

  Scaling test-time compute enhances long chain-of-thought (CoT) reasoning, yet existing approaches face a fundamental trade-off between computational cost and coverage quality: either incurring high training expense or yielding redundant trajectories. We introduce The Geometric Reasoner (TGR), a trai…

• Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning

  Jinyeop Song, Song Wang, Julian Shun, Yada Zhu · 28 janvier 2026

  Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucinations and expose reasoning traces. However, many KG-RAG systems compose multiple LLM modules (e.g planning, reasoning, and responding), i…

• FSD-CAP: Fractional Subgraph Diffusion with Class-Aware Propagation for Graph Feature Imputation

  Xin Qiao, Shijie Sun, Anqi Dong, Cong Hua, Xia Zhao, Longfei Zhang, Guangming Zhu, Liang Zhang · 28 janvier 2026

  Imputing missing node features in graphs is challenging, particularly under high missing rates. Existing methods based on latent representations or global diffusion often fail to produce reliable estimates, and may propagate errors across the graph. We propose FSD-CAP, a two-stage framework designed…

• GraIP: A Benchmarking Framework For Neural Graph Inverse Problems

  Semih Cant\"urk, Andrei Manolache, Arman Mielke, Chendi Qian, Antoine Siraudin, Christopher Morris, Mathias Niepert, Guy Wolf · 28 janvier 2026

  A wide range of graph learning tasks, such as structure discovery, temporal graph analysis, and combinatorial optimization, focus on inferring graph structures from data, rather than making predictions on given graphs. However, the respective methods to solve such problems are often developed in an …

• RPO-RAG: Aligning Small LLMs with Relation-aware Preference Optimization for Knowledge Graph Question Answering

  Kaehyun Um, KyuHwan Yeom, Haerim Yang, Minyoung Choi, Hyeongjun Yang, Kyong-Ho Lee · 28 janvier 2026

  Large Language Models (LLMs) have recently demonstrated remarkable reasoning abilities, yet hallucinate on knowledge-intensive tasks. Retrieval-augmented generation (RAG) mitigates this issue by grounding answers in external sources, e.g., knowledge graphs (KGs). However, existing KG-based RAG appro…

• XIMP: Cross Graph Inter-Message Passing for Molecular Property Prediction

  Anatol Ehrlich, Lorenz Kummer, Vojtech Voracek, Franka Bause, Nils M. Kriege · 28 janvier 2026

  Accurate molecular property prediction is central to drug discovery, yet graph neural networks often underperform in data-scarce regimes and fail to surpass traditional fingerprints. We introduce cross-graph inter-message passing (XIMP), which performs message passing both within and across multiple…

• GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning

  Chuanyue Yu, Kuo Zhao, Yuhan Li, Heng Chang, Mingjian Feng, Xiangzhe Jiang, Yufei Sun, Jia Li, Yuzhi Zhang, Jianxin Li, Ziwei Zhang · 28 janvier 2026

  Graph Retrieval-Augmented Generation (GraphRAG) has shown great effectiveness in enhancing the reasoning abilities of LLMs by leveraging graph structures for knowledge representation and modeling complex real-world relationships. However, existing GraphRAG methods still face significant bottlenecks …

• ASEHybrid: When Geometry Matters Beyond Homophily in Graph Neural Networks

  Shalima Binta Manir, Tim Oates · 28 janvier 2026

  Standard message-passing graph neural networks (GNNs) often struggle on graphs with low homophily, yet homophily alone does not explain this behavior, as graphs with similar homophily levels can exhibit markedly different performance and some heterophilous graphs remain easy for vanilla GCNs. Recent…

• A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction

  Jinkyu Sung, Myunggeum Jee, Joonseok Lee · 28 janvier 2026

  Link sign prediction on a signed graph is a task to determine whether the relationship represented by an edge is positive or negative. Since the presence of negative edges violates the graph homophily assumption that adjacent nodes are similar, regular graph methods have not been applicable without …

• OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detection

  Lecheng Zheng, Dongqi Fu, Zihao Li, Jingrui He · 28 janvier 2026

  Graph data is informative to represent complex relationships such as transactions between accounts, communications between devices, and dependencies among machines or processes. Correspondingly, graph anomaly detection (GAD) plays a critical role in identifying anomalies across various domains, incl…

• Fixed Aggregation Features Can Rival GNNs

  Celia Rubio-Madrigal, Rebekka Burkholz · 28 janvier 2026

  Graph neural networks (GNNs) are widely believed to excel at node representation learning through trainable neighborhood aggregations. We challenge this view by introducing Fixed Aggregation Features (FAFs), a training-free approach that transforms graph learning tasks into tabular problems. This si…

• $R^2$-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation

  Zhen Wu, Ritam Dutt, Luke M. Breitfeller, Armineh Nourbakhsh, Siddharth Parekh, Carolyn Ros\'e · 28 janvier 2026

  Relational reasoning lies at the core of many NLP tasks, drawing on complementary signals from text and graphs. While prior research has investigated how to leverage this dual complementarity, a detailed and systematic understanding of text-graph interplay and its effect on hybrid models remains und…

• FloydNet: A Learning Paradigm for Global Relational Reasoning

  Jingcheng Yu, Mingliang Zeng, Qiwei Ye · 28 janvier 2026

  Developing models capable of complex, multi-step reasoning is a central goal in artificial intelligence. While representing problems as graphs is a powerful approach, Graph Neural Networks (GNNs) are fundamentally constrained by their message-passing mechanism, which imposes a local bottleneck that …

• PEARL: Prototype-Enhanced Alignment for Label-Efficient Representation Learning with Deployment-Driven Insights from Digital Governance Communication Systems

  Ruiyu Zhang, Lin Nie, Wai-Fung Lam, Qihao Wang, Xin Zhao · 27 janvier 2026

  In many deployed systems, new text inputs are handled by retrieving similar past cases, for example when routing and responding to citizen messages in digital governance platforms. When these systems fail, the problem is often not the language model itself, but that the nearest neighbors in the embe…

• Resonant Sparse Geometry Networks

  Hasi Hays · 27 janvier 2026

  We introduce Resonant Sparse Geometry Networks (RSGN), a brain-inspired architecture with self-organizing sparse hierarchical input-dependent connectivity. Unlike Transformer architectures that employ dense attention mechanisms with O(n^2) computational complexity, RSGN embeds computational node…

• Implementing Tensor Logic: Unifying Datalog and Neural Reasoning via Tensor Contraction

  Swapn Shah (School of Data Science, University of North Carolina at Charlotte), Wlodek Zadrozny (Department of Computer Science, University of North Carolina at Charlotte) · 27 janvier 2026

  The unification of symbolic reasoning and neural networks remains a central challenge in artificial intelligence. Symbolic systems offer reliability and interpretability but lack scalability, while neural networks provide learning capabilities but sacrifice transparency. Tensor Logic, proposed by Do…

• OntoMetric: An Ontology-Driven LLM-Assisted Framework for Automated ESG Metric Knowledge Graph Generation

  Mingqin Yu (University of New South Wales, Sydney, Australia), Fethi Rabhi (University of New South Wales, Sydney, Australia), Boming Xia (University of Adelaide, Adelaide, Australia), Zhengyi Yang (University of New South Wales, Sydney, Australia), Felix Tan (University of New South Wales, Sydney, Australia), Qinghua Lu (CSIRO Data61, Sydney, Australia) · 27 janvier 2026

  Environmental, Social, and Governance (ESG) metric knowledge is inherently structured, connecting industries, reporting frameworks, metric categories, metrics, and calculation models through compositional dependencies, yet in practice this structure remains embedded implicitly in regulatory document…

• HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs

  Xinyue Zeng, Junhong Lin, Yujun Yan, Feng Guo, Liang Shi, Jun Wu, Dawei Zhou · 27 janvier 2026

  The reliability of Large Language Models (LLMs) in high-stakes domains such as healthcare, law, and scientific discovery is often compromised by hallucinations. These failures typically stem from two sources: data-driven hallucinations and reasoning-driven hallucinations. However, existing detection…

• RAG-GFM: Overcoming In-Memory Bottlenecks in Graph Foundation Models via Retrieval-Augmented Generation

  Haonan Yuan, Qingyun Sun, Jiacheng Tao, Xingcheng Fu, Jianxin Li · 27 janvier 2026

  Graph Foundation Models (GFMs) have emerged as a frontier in graph learning, which are expected to deliver transferable representations across diverse tasks. However, GFMs remain constrained by in-memory bottlenecks: they attempt to encode knowledge into model parameters, which limits semantic capac…