Advanced Graph Neural Networks

Derniers papiers

• InfGraND: An Influence-Guided GNN-to-MLP Knowledge Distillation

  Amir Eskandari, Aman Anand, Elyas Rashno, Farhana Zulkernine · 14 janvier 2026

  Graph Neural Networks (GNNs) are the go-to model for graph data analysis. However, GNNs rely on two key operations - aggregation and update, which can pose challenges for low-latency inference tasks or resource-constrained scenarios. Simple Multi-Layer Perceptrons (MLPs) offer a computationally effi…

• GraphFusionSBR: Denoising Multi-Channel Graphs for Session-Based Recommendation

  Jia-Xin He, Hung-Hsuan Chen · 14 janvier 2026

  Session-based recommendation systems must capture implicit user intents from sessions. However, existing models suffer from issues such as item interaction dominance and noisy sessions. We propose a multi-channel recommendation model, including a knowledge graph channel, a session hypergraph channel…

• Hyperbolic Heterogeneous Graph Transformer

  Jongmin Park, Seunghoon Han, Hyewon Lee, Won-Yong Shin, Sungsu Lim · 14 janvier 2026

  In heterogeneous graphs, we can observe complex structures such as tree-like or hierarchical structures. Recently, the hyperbolic space has been widely adopted in many studies to effectively learn these complex structures. Although these methods have demonstrated the advantages of the hyperbolic spa…

• Reliable Graph-RAG for Codebases: AST-Derived Graphs vs LLM-Extracted Knowledge Graphs

  Manideep Reddy Chinthareddy · 14 janvier 2026

  Retrieval-Augmented Generation for software engineering often relies on vector similarity search, which captures topical similarity but can fail on multi-hop architectural reasoning such as controller to service to repository chains, interface-driven wiring, and inheritance. This paper benchmarks th…

• Using Subgraph GNNs for Node Classification:an Overlooked Potential Approach

  Qian Zeng, Xin Lin, Jingyi Gao, Yang Yu · 14 janvier 2026

  Previous studies have demonstrated the strong performance of Graph Neural Networks (GNNs) in node classification. However, most existing GNNs adopt a node-centric perspective and rely on global message passing, leading to high computational and memory costs that hinder scalability. To mitigate these…

• Directed Homophily-Aware Graph Neural Network

  Aihu Zhang, Jiaxing Xu, Mengcheng Lan, Shili Xiang, Yiping Ke · 14 janvier 2026

  Graph Neural Networks (GNNs) have achieved significant success in various learning tasks on graph-structured data. Nevertheless, most GNNs struggle to generalize to heterophilic neighborhoods. Additionally, many GNNs ignore the directional nature of real-world graphs, resulting in suboptimal perform…

• GADPN: Graph Adaptive Denoising and Perturbation Networks via Singular Value Decomposition

  Hao Deng, Bo Liu · 14 janvier 2026

  While Graph Neural Networks (GNNs) excel on graph-structured data, their performance is fundamentally limited by the quality of the observed graph, which often contains noise, missing links, or structural properties misaligned with GNNs' underlying assumptions. To address this, graph structure learn…

• Demystifying the Slash Pattern in Attention: The Role of RoPE

  Yuan Cheng, Fengzhuo Zhang, Yunlong Hou, Cunxiao Du, Chao Du, Tianyu Pang, Aixin Sun, Zhuoran Yang · 14 janvier 2026

  Large Language Models (LLMs) often exhibit slash attention patterns, where attention scores concentrate along the $\Delta$-th sub-diagonal for some offset $\Delta$. These patterns play a key role in passing information across tokens. But why do they emerge? In this paper, we demystify the emergence …

• Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression

  Zijun Di, Bin Lu, Huquan Kang, Luoyi Fu, Jiaxin Ding, Xiaoying Gan, Lei Zhou, Xinbing Wang, Chenghu Zhou · 14 janvier 2026

  Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding. Recent studies typically focus on verbalizing the graph structures via handcrafted prompts, feeding the target node and its neighborhood context into LLMs. However, constrained by the …

• Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation

  Xiaoxiong Zhang, Zhiwei Zeng, Xin Zhou, Chunyan Miao · 13 janvier 2026

  Federated Knowledge Graph Embedding (FKGE) aims to facilitate collaborative learning of entity and relation embeddings from distributed Knowledge Graphs (KGs) across multiple clients, while preserving data privacy. Training FKGE models with higher dimensions is typically favored due to their potenti…

• Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophily

  Haitong Luo, Suhang Wang, Weiyao Zhang, Ruiqi Meng, Xuying Meng, Yujun Zhang · 13 janvier 2026

  Graph ``pre-training and prompt-tuning'' aligns downstream tasks with pre-trained objectives to enable efficient knowledge transfer under limited supervision. However, current methods typically rely on single-filter backbones (e.g., low-pass), whereas real-world graphs exhibit inherent spectral dive…

• Position: Don't be Afraid of Over-Smoothing And Over-Squashing

  Niklas Kormann, Benjamin Doerr, Johannes F. Lutzeyer · 13 janvier 2026

  Over-smoothing and over-squashing have been extensively studied in the literature on Graph Neural Networks (GNNs) over the past years. We challenge this prevailing focus in GNN research, arguing that these phenomena are less critical for practical applications than assumed. We suggest that performan…

• Learning to Evolve: Bayesian-Guided Continual Knowledge Graph Embedding

  Linyu Li, Zhi Jin, Yuanpeng He, Dongming Jin, Yichi Zhang, Haoran Duan, Xuan Zhang, Zhengwei Tao, Nyima Tash · 13 janvier 2026

  As social media and the World Wide Web become hubs for information dissemination, effectively organizing and understanding the vast amounts of dynamically evolving Web content is crucial. Knowledge graphs (KGs) provide a powerful framework for structuring this information. However, the rapid emergen…

• Graph Attention Specialized Expert Fusion Model for Node Classification: Based on Cora and Pubmed Datasets

  Zihang Ma, Qitian Yin · 13 janvier 2026

  Graph node classification is a fundamental task in graph neural networks (GNNs), aiming to assign predefined class labels to nodes. On the PubMed citation network dataset, we observe significant classification difficulty disparities, with Category 2 achieving only 74.4% accuracy in traditional GCN, …

• LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing

  Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu · 13 janvier 2026

  Large language model (LLM) routing assigns each query to the most suitable model from an ensemble. We introduce LLMRouterBench, a large-scale benchmark and unified framework for LLM routing. It comprises over 400K instances from 21 datasets and 33 models. Moreover, it provides comprehensive metrics …

• L2CU: Learning to Complement Unseen Users

  Dileepa Pitawela, Gustavo Carneiro, Hsiang-Ting Chen · 13 janvier 2026

  Recent research highlights the potential of machine learning models to learn to complement (L2C) human strengths; however, generalizing this capability to unseen users remains a significant challenge. Existing L2C methods oversimplify interaction between human and AI by relying on a single, global u…

• What Breaks Knowledge Graph based RAG? Benchmarking and Empirical Insights into Reasoning under Incomplete Knowledge

  Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Yuan He, Jiaoyan Chen, Steffen Staab, Evgeny Kharlamov · 13 janvier 2026

  Knowledge Graph-based Retrieval-Augmented Generation (KG-RAG) is an increasingly explored approach for combining the reasoning capabilities of large language models with the structured evidence of knowledge graphs. However, current evaluation practices fall short: existing benchmarks often include q…

• Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG

  Manzong Huang, Chenyang Bu, Yi He, Xingrui Zhuo, Xindong Wu · 13 janvier 2026

  Graph-based Retrieval-Augmented Generation (GraphRAG) mitigates hallucinations in Large Language Models (LLMs) by grounding them in structured knowledge. However, current GraphRAG methods are constrained by a prevailing \textit{build-then-reason} paradigm, which relies on a static, pre-constructed K…

• Ontology Neural Networks for Topologically Conditioned Constraint Satisfaction

  Jaehong Oh · 12 janvier 2026

  Neuro-symbolic reasoning systems face fundamental challenges in maintaining semantic coherence while satisfying physical and logical constraints. Building upon our previous work on Ontology Neural Networks, we present an enhanced framework that integrates topological conditioning with gradient stabi…

• Cumulative Path-Level Semantic Reasoning for Inductive Knowledge Graph Completion

  Jiapu Wang, Xinghe Cheng, Zezheng Wu, Ruiqi Ma, Rui Wang, Zhichao Yan, Haoran Luo, Yuhao Jiang, Kai Sun · 12 janvier 2026

  Conventional Knowledge Graph Completion (KGC) methods aim to infer missing information in incomplete Knowledge Graphs (KGs) by leveraging existing information, which struggle to perform effectively in scenarios involving emerging entities. Inductive KGC methods can handle the emerging entities and r…

• Improving Enzyme Prediction with Chemical Reaction Equations by Hypergraph-Enhanced Knowledge Graph Embeddings

  Tengwei Song, Long Yin, Zhen Han, Zhiqiang Xu · 12 janvier 2026

  Predicting enzyme-substrate interactions has long been a fundamental problem in biochemistry and metabolic engineering. While existing methods could leverage databases of expert-curated enzyme-substrate pairs for models to learn from known pair interactions, the databases are often sparse, i.e., the…

• Manifold limit for the training of shallow graph convolutional neural networks

  Johanna Tengler, Christoph Brune, Jos\'e A. Iglesias · 12 janvier 2026

  We study the discrete-to-continuum consistency of the training of shallow graph convolutional neural networks (GCNNs) on proximity graphs of sampled point clouds under a manifold assumption. Graph convolution is defined spectrally via the graph Laplacian, whose low-frequency spectrum approximates th…

• Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts

  Wei Zhou, Hong Huang, Ruize Shi, Bang Liu · 12 janvier 2026

  Heterogeneous Graph Neural Networks(HGNNs) have advanced mainly through better encoders, yet their decoding/projection stage still relies on a single shared linear head, assuming it can map rich node embeddings to labels. We call this the Linear Projection Bottleneck: in heterogeneous graphs, contex…

• DynaSTy: A Framework for SpatioTemporal Node Attribute Prediction in Dynamic Graphs

  Namrata Banerji, Tanya Berger-Wolf · 12 janvier 2026

  Accurate multistep forecasting of node-level attributes on dynamic graphs is critical for applications ranging from financial trust networks to biological networks. Existing spatiotemporal graph neural networks typically assume a static adjacency matrix. In this work, we propose an end-to-end dynami…

• Graph-Dictionary Signal Model for Sparse Representations of Multivariate Data

  William Cappelletti, Pascal Frossard · 9 janvier 2026

  Representing and exploiting multivariate signals requires capturing relations between variables, which we can represent by graphs. Graph dictionaries allow to describe complex relational information as a sparse sum of simpler structures, but no prior model exists to infer such underlying structure e…