Advanced Graph Neural Networks

Derniers papiers

• BoostFGL: Boosting Fairness in Federated Graph Learning

  Zekai Chen, Kairui Yang, Xunkai Li, Henan Sun, Zhihan Zhang, Jia Li, Qiangqiang Dai, Rong-Hua Li, Guoren Wang · 26 janvier 2026

  Federated graph learning (FGL) enables collaborative training of graph neural networks (GNNs) across decentralized subgraphs without exposing raw data. While existing FGL methods often achieve high overall accuracy, we show that this average performance can conceal severe degradation on disadvantage…

• Analyzing Neural Network Information Flow Using Differential Geometry

  Shuhang Tan, Jayson Sia, Paul Bogdan, Radoslav Ivanov · 26 janvier 2026

  This paper provides a fresh view of the neural network (NN) data flow problem, i.e., identifying the NN connections that are most important for the performance of the full model, through the lens of graph theory. Understanding the NN data flow provides a tool for symbolic NN analysis, e.g.,~robustne…

• Towards Open-World Retrieval-Augmented Generation on Knowledge Graph: A Multi-Agent Collaboration Framework

  Jiasheng Xu, Mingda Li, Yongqiang Tang, Peijie Wang, Wensheng Zhang · 26 janvier 2026

  Large Language Models (LLMs) have demonstrated strong capabilities in web search and reasoning. However, their dependence on static training corpora makes them prone to factual errors and knowledge gaps. Retrieval-Augmented Generation (RAG) addresses this limitation by incorporating external knowled…

• Calibrated Similarity for Reliable Geometric Analysis of Embedding Spaces

  Nicolas Tacheny · 26 janvier 2026

  While raw cosine similarity in pretrained embedding spaces exhibits strong rank correlation with human judgments, anisotropy induces systematic miscalibration of absolute values: scores concentrate in a narrow high-similarity band regardless of actual semantic relatedness, limiting interpretability …

• DANCE: Dynamic, Available, Neighbor-gated Condensation for Federated Text-Attributed Graphs

  Zekai Chen, Haodong Lu, Xunkai Li, Henan Sun, Jia Li, Hongchao Qin, Rong-Hua Li, Guoren Wang · 26 janvier 2026

  Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. With the rise of large language models (LLMs), textual attributes in FGL graphs are gaining attention. Text-attributed graph federated learning (TAG-FGL) improves FGL by explicitly leveraging LLMs to…

• Multi-Targeted Graph Backdoor Attack

  Md Nabi Newaz Khan, Abdullah Arafat Miah, Yu Bi · 23 janvier 2026

  Graph neural network (GNN) have demonstrated exceptional performance in solving critical problems across diverse domains yet remain susceptible to backdoor attacks. Existing studies on backdoor attack for graph classification are limited to single target attack using subgraph replacement based mecha…

• Communication-efficient Federated Graph Classification via Generative Diffusion Modeling

  Xiuling Wang, Xin Huang, Haibo Hu, Jianliang Xu · 23 janvier 2026

  Graph Neural Networks (GNNs) unlock new ways of learning from graph-structured data, proving highly effective in capturing complex relationships and patterns. Federated GNNs (FGNNs) have emerged as a prominent distributed learning paradigm for training GNNs over decentralized data. However, FGNNs fa…

• Logic Programming on Knowledge Graph Networks And its Application in Medical Domain

  Chuanqing Wang, Zhenmin Zhao, Shanshan Du, Chaoqun Fei, Songmao Zhang, Ruqian Lu · 23 janvier 2026

  The rash development of knowledge graph research has brought big driving force to its application in many areas, including the medicine and healthcare domain. However, we have found that the application of some major information processing techniques on knowledge graph still lags behind. This defect…

• Improving MoE Compute Efficiency by Composing Weight and Data Sparsity

  Maciej Kilian, Oleg Mkrtchyan, Luke Zettlemoyer, Akshat Shrivastava, Armen Aghajanyan · 23 janvier 2026

  Mixture-of-Experts layers achieve compute efficiency through weight sparsity: each token activates only a subset of experts. Data sparsity, where each expert processes only a subset of tokens, offers a complementary axis. Expert-choice routing implements data sparsity directly but violates causality…

• A tensor network formalism for neuro-symbolic AI

  Alex Goessmann, Janina Sch\"utte, Maximilian Fr\"ohlich, Martin Eigel · 23 janvier 2026

  The unification of neural and symbolic approaches to artificial intelligence remains a central open challenge. In this work, we introduce a tensor network formalism, which captures sparsity principles originating in the different approaches in tensor decompositions. In particular, we describe a basi…

• FSX: Message Flow Sensitivity Enhanced Structural Explainer for Graph Neural Networks

  Bizu Feng, Zhimu Yang, Shaode Yu, Zixin Hu · 22 janvier 2026

  Despite the widespread success of Graph Neural Networks (GNNs), understanding the reasons behind their specific predictions remains challenging. Existing explainability methods face a trade-off that gradient-based approaches are computationally efficient but often ignore structural interactions, whi…

• LoRAP: Low-Rank Aggregation Prompting for Quantized Graph Neural Networks Training

  Chenyu Liu, Haige Li, Luca Rossi · 22 janvier 2026

  Graph Neural Networks (GNNs) are neural networks that aim to process graph data, capturing the relationships and interactions between nodes using the message-passing mechanism. GNN quantization has emerged as a promising approach for reducing model size and accelerating inference in resource-constra…

• Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems

  Shuhua Yang, Jiahao Zhang, Yilong Wang, Dongwon Lee, Suhang Wang · 22 janvier 2026

  Graph-based retrieval-augmented generation (GraphRAG) systems construct knowledge graphs over document collections to support multi-hop reasoning. While prior work shows that GraphRAG responses may leak retrieved subgraphs, the feasibility of query-efficient reconstruction of the hidden graph struct…

• A Survey of Quantized Graph Representation Learning: Connecting Graph Structures with Large Language Models

  Qika Lin, Zhen Peng, Kaize Shi, Kai He, Yiming Xu, Jian Zhang, Erik Cambria, Mengling Feng · 22 janvier 2026

  Recent years have witnessed rapid advances in graph representation learning, with the continuous embedding approach emerging as the dominant paradigm. However, such methods encounter issues regarding parameter efficiency, interpretability, and robustness. Thus, Quantized Graph Representation (QGR) l…

• PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking Mechanism

  Ningyuan Li, Junrui Liu, Yi Shan, Minghui Huang, Ziren Gong, Tong Li · 22 janvier 2026

  Recent graph-based RAG approaches leverage knowledge graphs by extracting entities from a query to fetch their associated relationships and metadata. However, relying solely on entity extraction often results in the misinterpretation or omission of latent critical information and relationships. This…

• GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attention

  Junchi Yan, Fangyu Ding, Jiawei Sun, Zhaoping Hu, Yunyi Zhou, Lei Zhu · 22 janvier 2026

  Graph invariant learning (GIL) seeks invariant relations between graphs and labels under distribution shifts. Recent works try to extract an invariant subgraph to improve out-of-distribution (OOD) generalization, yet existing approaches either lack explicit control over compactness or rely on hard t…

• Bridging the Gap Between Simulated and Real Network Data Using Transfer Learning

  Carlos G\"uemes-Palau, Miquel Ferriol-Galm\'es, Jordi Paillisse-Vilanova, Albert L\'opez-Bresc\'o, Pere Barlet-Ros, Albert Cabellos-Aparicio · 22 janvier 2026

  Machine Learning (ML)-based network models provide fast and accurate predictions for complex network behaviors but require substantial training data. Collecting such data from real networks is often costly and limited, especially for critical scenarios like failures. As a result, researchers commonl…

• Re-understanding Graph Unlearning through Memorization

  Pengfei Ding, Yan Wang, Guanfeng Liu · 22 janvier 2026

  Graph unlearning (GU), which removes nodes, edges, or features from trained graph neural networks (GNNs), is crucial in Web applications where graph data may contain sensitive, mislabeled, or malicious information. However, existing GU methods lack a clear understanding of the key factors that deter…

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

  Haonan Yuan, Qingyun Sun, Jiacheng Tao, Xingcheng Fu, Jianxin Li · 22 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…

• To Neuro-Symbolic Classification and Beyond by Compiling Description Logic Ontologies to Probabilistic Circuits

  Nicolas Lazzari, Valentina Presutti, Antonio Vergari · 22 janvier 2026

  Background: Neuro-symbolic methods enhance the reliability of neural network classifiers through logical constraints, but they lack native support for ontologies. Objectives: We aim to develop a neuro-symbolic method that reliably outputs predictions consistent with a Description Logic ontology th…

• Beyond Single-Granularity Prompts: A Multi-Scale Chain-of-Thought Prompt Learning for Graph

  Ziyu Zheng, Yaming Yang, Ziyu Guan, Wei Zhao, Xinyan Huang, Weigang Lu · 22 janvier 2026

  The ``pre-train, prompt" paradigm, designed to bridge the gap between pre-training tasks and downstream objectives, has been extended from the NLP domain to the graph domain and has achieved remarkable progress. Current mainstream graph prompt-tuning methods modify input or output features using lea…

• Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning

  Yuval Kansal, Niraj K. Jha · 22 janvier 2026

  Large language models have achieved near-expert performance in structured reasoning domains like mathematics and programming, yet their ability to perform compositional multi-hop reasoning in specialized scientific fields remains limited. We propose a bottom-up learning paradigm in which models are …

• Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data

  Yuval Ran-Milo, Yotam Alexander, Shahar Mendel, Nadav Cohen · 22 janvier 2026

  Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive gradient descent to discover such systematic reasoning remains poorly…

• Topology-Aware Multiscale Mixture of Experts for Efficient Molecular Property Prediction

  Long D. Nguyen, Kelin Xia, Binh P. Nguyen · 21 janvier 2026

  Many molecular properties depend on 3D geometry, where non-covalent interactions, stereochemical effects, and medium- to long-range forces are determined by spatial distances and angles that cannot be uniquely captured by a 2D bond graph. Yet most 3D molecular graph neural networks still rely on glo…

• Data-centric Prompt Tuning for Dynamic Graphs

  Yufei Peng, Cheng Yang, Zhengjie Fan, Chuan Shi · 21 janvier 2026

  Dynamic graphs have attracted increasing attention due to their ability to model complex and evolving relationships in real-world scenarios. Traditional approaches typically pre-train models using dynamic link prediction and directly apply the resulting node temporal embeddings to specific downstrea…