Advanced Graph Neural Networks

Derniers papiers

• Guiding Federated Graph Recommendation with LLM-encoded knowledge

  Thi Minh Chau Nguyen, Hien Trang Nguyen, Duc Anh Nguyen, Van Ho-Long, Thanh Trung Huynh, Zhao Ren · 16 juin 2026

  Graph-based recommender systems are highly effective at extracting collaborative signals from user--item interactions, and federated learning (FL) allows these models to be trained while preserving user privacy. However, aggregating graph representations across distributed, non-IID clients remains a…

• Feature Attribution in Directed Acyclic Graphs Using Edge Intervention

  Qiheng Sun, Junxu Liu, Xiaokai Mao, Haocheng Xia, Jinfei Liu, Kui Ren, Haibo Hu · 16 juin 2026

  Shapley value-based feature attribution methods face challenges in scenarios involving complex feature interactions and causal relationships, even when a causal structure is provided. Existing methods typically adopt a node-centric view, attributing importance solely to individual features. Conseque…

• AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration

  Bing Hao, Ruijie Wang, Haodong Qian, Yunlong Chu, Yuhang Liu, Yumeng Lin, Minglai Shao, Jianxin Li · 16 juin 2026

  Large Language Models (LLMs) demonstrate remarkable potential in dynamic graph reasoning, but suffer from a scaling bottleneck: current models can only handle graphs with tens of nodes, constrained by exponential reasoning overhead and finite context windows. While multi-agent systems (MAS) offer co…

• Model Graph Inductive Learning for Knowledge Graph Completion

  Mohommad Esmaei Khani, Mahdieh Hasheminejad, Ali Taherkhani, Hossein Hajiabolhassan · 16 juin 2026

  Link prediction in knowledge graphs fundamentally depends on the quality of learned embeddings for entities and relations. However, most existing methods derive these embeddings by aggregating only the local neighborhood of each entity, neglecting the global structure of the knowledge graph. This li…

• Graph Learning Should Move Beyond Restrictive Views of Spectral and Message-Passing GNNs

  Antonis Vasileiou, Juan Cervino, Pascal Frossard, Charilaos I. Kanatsoulis, Christopher Morris, Michael T. Schaub, Pierre Vandergheynst, Zhiyang Wang, Guy Wolf, Ron Levie · 16 juin 2026

  Graph neural networks (GNNs) are commonly divided into message-passing neural networks (MPNNs) and spectral GNNs, reflecting two largely separate research traditions in machine learning and signal processing. While MPNNs have a precise definition, there is no widely accepted criterion for what makes…

• GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging

  Chen Zhao, Huan Huang, Yixin Xie, Jiajing Huang, Weihua Zhou · 16 juin 2026

  Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that affects millions of older adults, with prevalence expected to rise significantly in the coming years. Early diagnosis, particularly during the mild cognitive impairment (MCI) stage, is critical for timely intervention. Structu…

• TCHG: Tri-Trust Conditioned Heterogeneous Graph Learning for Reliable Dynamic Trust Prediction

  Bohao Liao, Boyu Deng, Qipeng Song, Jieling Wang, Jingchao Wang · 16 juin 2026

  Trust prediction infers latent user-user trust relations and provides important support for social recommendation, fake-review and manipulation detection, and risk identification. Graph neural networks have become a prominent approach to trust prediction because of their ability to learn network str…

• Filtered Conformal Ellipsoids for Graph-Native Time Series

  Yannick Limmer · 16 juin 2026

  Joint prediction sets for multivariate time series should control a single event while adapting to cross-coordinate dependence. We study filtered conformal ellipsoids: a frozen state-space filter emits a one-step predictive mean and covariance, and split-conformal calibration is applied to the resul…

• Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs

  Sahil Rajesh Dhayalkar · 16 juin 2026

  Modern artificial intelligence remains fundamentally divided between the continuous, probabilistic spaces of Foundation Models and the discrete, deterministic structures of Knowledge Graphs. While Retrieval-Augmented Generation (RAG) attempts to connect them by serializing graph data into text, we a…

• ACC: Compiling Agent Trajectories for Long-Context Training

  Qisheng Su, Zhen Fang, Shiting Huang, Yu Zeng, Yiming Zhao, Kou Shi, Ziao Zhang, Lin Chen, Zehui Chen, Lijun Wu, Feng Zhao · 16 juin 2026

  Recent development of agents has renewed demand for long-context reasoning capacity of LLMs. However, training LLMs for this capacity requires costly long-document curation or heuristic context synthesis. We observe that agents produce massive trajectories when solving problems, invoking tools and r…

• Formalizing and Mitigating Structural Distortion in LLM Attention for Zero-Shot Graph Reasoning

  Donald Loveland, Puja Trivedi, Ari Weinstein, Edward W Huang, Danai Koutra · 16 juin 2026

  Large Language Models (LLMs) have shown promise for reasoning over Text-Attributed Graphs (TAGs). However, applying LLMs to graphs requires linearizing their structure into sequences, introducing distortion rooted in the graph bandwidth problem. While this distortion has been shown to degrade perfor…

• Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci Flow

  Tian Qin, Wei-Min Huang · 16 juin 2026

  Ricci flow is a curvature-guided diffusion process that deforms space by shrinking regions of high positive curvature and expanding those with negative curvature. Similarly, discrete Ricci flow on weighted graphs modifies edge weights by shrinking edges with positive Ricci curvature and stretching t…

• Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graph Generation

  Mohammad Sadeq Abolhasani, Yang Ba, Yixuan He, Rong Pan · 16 juin 2026

  Knowledge graph generation typically relies either on predefined ontologies or on schema-free extraction. Ontology-driven pipelines enforce consistent typing but require costly schema design and maintenance, whereas schema-free methods often produce fragmented graphs with weak global organization, e…

• TechRAG: Evidence-Gated Multimodal Agentic RAG for Technical Literature Reasoning

  Kanwar Bharat Singh · 16 juin 2026

  This paper presents an agentic multimodal retrieval-augmented generation (RAG) framework for domain-specific literature reasoning, instantiated on a curated corpus of several thousand papers in intelligent tires, vehicle dynamics, vehicle control, sensing, estimation, and machine learning. Unlike co…

• Controlled Dynamics Attractor Transformer

  Cheng Zhang, Minnan Luo, Zesheng Yang, Ming Li, Yong-Jin Liu, Qinghua Zheng · 16 juin 2026

  Transformer architectures have dramatically advanced representation learning and inference in deep models through self-attention mechanisms. In parallel,associative memory (AM) frameworks map representations onto energy landscapes, offering interpretable retrieval mechanisms. However, their continuo…

• Multi-Granular Node Pruning for Causal Circuit Discovery

  Muhammad Umair Haider, Hammad Rizwan, Hassan Sajjad, A. B. Siddique · 16 juin 2026

  Circuit discovery aims to identify minimal subnetworks that are responsible for specific behaviors in large language models (LLMs). Existing approaches primarily rely on iterative edge pruning, which is computationally expensive and limited to coarse-grained units such as attention heads or MLP bloc…

• AdaMame: A Training Recipe for Adaptive Multilingual Reasoning

  Dayeon Ki, Kevin Duh, Marine Carpuat · 16 juin 2026

  While Large Reasoning Models (LRMs) show strong performance in English, they often fail to reason in the language of the query, a phenomenon known as language collapse. Existing RL-based fixes typically add a binary language fidelity reward to the accuracy objective, yet still incur trade-off in acc…

• Achieving Precise Text-To-Cypher Via Grounded Knowledge Graph Data Generation

  Francesco Cazzaro, Jessica Lennon, Ariadna Quattoni · 15 juin 2026

  Property Graphs are rapidly being adopted as database frameworks for representing heterogeneous data sources. To enable precise access to the information contained in them we need conversational interfaces based on Text-To-Cypher (Text2Cypher) parsers. This paper presents an automatic synthetic data…

• GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging

  Chen Zhao, Huan Huang, Yixin Xie, Jiajing Huang, Weihua Zhou, Nandakumar Narayanan · 15 juin 2026

  Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that affects millions of older adults, with prevalence expected to rise significantly in the coming years. Early diagnosis, particularly during the mild cognitive impairment (MCI) stage, is critical for timely intervention. Structu…

• Recipe-Controlled Decoder Audit for Structural Knowledge-Graph Completion

  Xihang Shan, Ye Luo · 15 juin 2026

  We present a recipe-controlled decoder audit (RCDA) for structural transductive knowledge-graph completion (KGC). The audit asks a simple reporting question: before attributing gains to an encoder or training recipe, what changes when the decoder is swapped under the same recipe? Using ComplEx and D…

• Context-aware Modality-Topology Co-Alignment for Multimodal Attributed Graphs

  Sirui Zhang, Xu Wang, Zhengyu Wu, Xunkai Li, Hongchao Qin · 15 juin 2026

  Multimodal Attributed Graphs (MAGs) model real-world entities by coupling graph topology with heterogeneous attributes such as text and images. They support graph-centric tasks requiring structural and class-discriminative representations, and modality-centric tasks requiring fine-grained cross-moda…

• Beyond a Single Explanation of the Adam--SGD Gap

  Chenxiang Zhang, Rustem Islamov, Enea Monzio Compagnoni, Jun Pang, Aurelien Lucchi, Antonio Orvieto · 15 juin 2026

  Prior work has identified several factors that can contribute to the performance gap between Adam and SGD, spanning data aspects, architecture design, and optimization properties. Yet these explanations are often studied in isolation, leaving their relative importance unclear. In this work, we revis…

• GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs

  Zhuoyi Peng, Jingzhou Jiang, Hanlin Gu, Lixin Fan, Yi Yang · 12 juin 2026

  Graph analysis underlies many applications whose answers cannot be looked up in a single record or retrieved along a path: laundering rings, drug repurposing, user preference, and scientific theme are all inferred from a node together with its neighbourhood. We introduce GraphInfer-Bench, a benchmar…

• A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction

  Phan Nguyen, Dat Cao, Hien Chu, Khue Hoang · 12 juin 2026

  Cross-domain graph anomaly detection (GAD) aims to identify abnormal nodes in unseen target graphs, showing strong potential in real-world applications with heterogeneous graph data. However, existing methods often depend on dataset-specific feature semantics and structural patterns, which limits th…

• Graph Reduction in Multirelational Networks: A Spreading-Oriented Reduction Benchmark

  Mateusz Stolarski, Micha{\l} Czuba, Piotr Bielak, Piotr Br\'odka · 12 juin 2026

  Real-world networks are inherently incomplete, noisy, and dynamically evolving, making it difficult to capture all actors and their relationships. Their scale often renders direct analysis computationally demanding. While influence maximisation (IM) has been widely studied, the role of graph reducti…