Advanced Graph Neural Networks

Derniers papiers

• PINE: Pipeline for Important Node Exploration in Attributed Networks

  Elizaveta Kovtun, Maksim Makarenko, Natalia Semenova, Alexey Zaytsev, Semen Budennyy · 9 décembre 2025

  A graph with semantically attributed nodes are a common data structure in a wide range of domains. It could be interlinked web data or citation networks of scientific publications. The essential problem for such a data type is to determine nodes that carry greater importance than all the others, a t…

• Towards a Relationship-Aware Transformer for Tabular Data

  Andrei V. Konstantinov, Valerii A. Zuev, Lev V. Utkin · 9 décembre 2025

  Deep learning models for tabular data typically do not allow for imposing a graph of external dependencies between samples, which can be useful for accounting for relatedness in tasks such as treatment effect estimation. Graph neural networks only consider adjacent nodes, making them difficult to ap…

• Learning to Select MCP Algorithms: From Traditional ML to Dual-Channel GAT-MLP

  Xiang Li, Shanshan Wang, Chenglong Xiao · 9 décembre 2025

  The Maximum Clique Problem (MCP) is a foundational NP-hard problem with wide-ranging applications, yet no single algorithm consistently outperforms all others across diverse graph instances. This underscores the critical need for instance-aware algorithm selection, a domain that remains largely unex…

• SDT-GNN: Streaming-based Distributed Training Framework for Graph Neural Networks

  Xin Huang, Weipeng Zhuo, Minh Phu Vuong, Shiju Li, Jongryool Kim, Bradley Rees, Chul-Ho Lee · 9 décembre 2025

  Recently, distributed GNN training frameworks, such as DistDGL and PyG, have been developed to enable training GNN models on large graphs by leveraging multiple GPUs in a distributed manner. Despite these advances, their memory requirements are still excessively high, thereby hindering GNN training …

• Flatten Graphs as Sequences: Transformers are Scalable Graph Generators

  Dexiong Chen, Markus Krimmel, Karsten Borgwardt · 9 décembre 2025

  We introduce AutoGraph, a scalable autoregressive model for attributed graph generation using decoder-only transformers. By flattening graphs into random sequences of tokens through a reversible process, AutoGraph enables modeling graphs as sequences without relying on additional node features that …

• Learning Conditional Independence Differential Graphs From Time-Dependent Data

  Jitendra K Tugnait · 9 décembre 2025

  Estimation of differences in conditional independence graphs (CIGs) of two time series Gaussian graphical models (TSGGMs) is investigated where the two TSGGMs are known to have similar structure. The TSGGM structure is encoded in the inverse power spectral density (IPSD) of the time series. In sever…

• Forget and Explain: Transparent Verification of GNN Unlearning

  Imran Ahsan (Department of Smart Cities, Chung-Ang University), Hyunwook Yu (Department of Computer Science and Engineering, Chung-Ang University), Jinsung Kim (Department of Computer Science and Engineering, Chung-Ang University), Mucheol Kim (Department of Computer Science and Engineering, Chung-Ang University) · 9 décembre 2025

  Graph neural networks (GNNs) are increasingly used to model complex patterns in graph-structured data. However, enabling them to "forget" designated information remains challenging, especially under privacy regulations such as the GDPR. Existing unlearning methods largely optimize for efficiency and…

• Repetition Makes Perfect: Recurrent Graph Neural Networks Match Message-Passing Limit

  Eran Rosenbluth, Martin Grohe · 9 décembre 2025

  We precisely characterize the expressivity of computable Recurrent Graph Neural Networks (recurrent GNNs). We prove that recurrent GNNs with finite-precision parameters, sum aggregation, and ReLU activation, can compute any graph algorithm that respects the natural message-passing invariance induced…

• Mind The Gap: Quantifying Mechanistic Gaps in Algorithmic Reasoning via Neural Compilation

  Lucas Saldyt, Subbarao Kambhampati · 9 décembre 2025

  This paper aims to understand how neural networks learn algorithmic reasoning by addressing two questions: How faithful are learned algorithms when they are effective, and why do neural networks fail to learn effective algorithms otherwise? To answer these questions, we use neural compilation, a tec…

• Dual Refinement Cycle Learning: Unsupervised Text Classification of Mamba and Community Detection on Text Attributed Graph

  Hong Wang, Yinglong Zhang, Hanhan Guo, Xuewen Xia, Xing Xu · 9 décembre 2025

  Pretrained language models offer strong text understanding capabilities but remain difficult to deploy in real-world text-attributed networks due to their heavy dependence on labeled data. Meanwhile, community detection methods typically ignore textual semantics, limiting their usefulness in downstr…

• Semi-supervised Graph Anomaly Detection via Robust Homophily Learning

  Guoguo Ai, Hezhe Qiao, Hui Yan, Guansong Pang · 9 décembre 2025

  Semi-supervised graph anomaly detection (GAD) utilizes a small set of labeled normal nodes to identify abnormal nodes from a large set of unlabeled nodes in a graph. Current methods in this line posit that 1) normal nodes share a similar level of homophily and 2) the labeled normal nodes can well re…

• Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design

  Jiannan Yang, Veronika Thost, Tengfei Ma · 9 décembre 2025

  Self-supervised learning (SSL) plays a central role in molecular representation learning. Yet, many recent innovations in masking-based pretraining are introduced as heuristics and lack principled evaluation, obscuring which design choices are genuinely effective. This work cast the entire pretrain-…

• Measuring Over-smoothing beyond Dirichlet energy

  Weiqi Guan, Zihao Shi · 9 décembre 2025

  While Dirichlet energy serves as a prevalent metric for quantifying over-smoothing, it is inherently restricted to capturing first-order feature derivatives. To address this limitation, we propose a generalized family of node similarity measures based on the energy of higher-order feature derivative…

• Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets

  Chang Liu, Vivian Li, Linus Leong, Vladimir Radenkovic, Pietro Li\`o, Chaitanya K. Joshi · 9 décembre 2025

  Geometric Graph Neural Networks (GNNs) and Transformers have become state-of-the-art for learning from 3D protein structures. However, their reliance on message passing prevents them from capturing the hierarchical interactions that govern protein function, such as global domains and long-range allo…

• DDFI: Diverse and Distribution-aware Missing Feature Imputation via Two-step Reconstruction

  Yifan Song, Fenglin Yu, Yihong Luo, Xingjian Tao, Siya Qiu, Kai Han, Jing Tang · 9 décembre 2025

  Incomplete node features are ubiquitous in real-world scenarios, e.g., the attributes of web users may be partly private, which causes the performance of Graph Neural Networks (GNNs) to decline significantly. Feature propagation (FP) is a well-known method that performs well for imputation of missin…

• Back to Author Console Empowering GNNs for Domain Adaptation via Denoising Target Graph

  Haiyang Yu, Meng-Chieh Lee, Xiang song, Qi Zhu, Christos Faloutsos · 9 décembre 2025

  We explore the node classification task in the context of graph domain adaptation, which uses both source and target graph structures along with source labels to enhance the generalization capabilities of Graph Neural Networks (GNNs) on target graphs. Structure domain shifts frequently occur, especi…

• Learning Invariant Graph Representations Through Redundant Information

  Barproda Halder, Pasan Dissanayake, Sanghamitra Dutta · 9 décembre 2025

  Learning invariant graph representations for out-of-distribution (OOD) generalization remains challenging because the learned representations often retain spurious components. To address this challenge, this work introduces a new tool from information theory called Partial Information Decomposition …

• Local-Curvature-Aware Knowledge Graph Embedding: An Extended Ricci Flow Approach

  Zhengquan Luo, Guy Tadmor, Or Amar, David Zeevi, Zhiqiang Xu · 9 décembre 2025

  Knowledge graph embedding (KGE) relies on the geometry of the embedding space to encode semantic and structural relations. Existing methods place all entities on one homogeneous manifold, Euclidean, spherical, hyperbolic, or their product/multi-curvature variants, to model linear, symmetric, or hier…

• FedIFL: A federated cross-domain diagnostic framework for motor-driven systems with inconsistent fault modes

  Zexiao Wang, Yankai Wang, Xiaoqiang Liao, Xinguo Ming, Weiming Shen · 8 décembre 2025

  Due to the scarcity of industrial data, individual equipment users, particularly start-ups, struggle to independently train a comprehensive fault diagnosis model; federated learning enables collaborative training while ensuring data privacy, making it an ideal solution. However, the diversity of wor…

• QoSDiff: An Implicit Topological Embedding Learning Framework Leveraging Denoising Diffusion and Adversarial Attention for Robust QoS Prediction

  Guanchen Du, Jianlong Xu, Wei Wei · 8 décembre 2025

  Accurate Quality of Service (QoS) prediction is fundamental to service computing, providing essential data-driven guidance for service selection and ensuring superior user experiences. However, prevalent approaches, particularly Graph Neural Networks (GNNs), heavily rely on constructing explicit use…

• Debate over Mixed-knowledge: A Robust Multi-Agent Reasoning Framework for Incomplete Knowledge Graph Question Answering

  Jilong Liu, Pengyang Shao, Wei Qin, Fei Liu, Yonghui Yang, Richang Hong · 8 décembre 2025

  Knowledge Graph Question Answering (KGQA) aims to improve factual accuracy by leveraging structured knowledge. However, real-world Knowledge Graphs (KGs) are often incomplete, leading to the problem of Incomplete KGQA (IKGQA). A common solution is to incorporate external data to fill knowledge gaps,…

• Edged Weisfeiler-Lehman Algorithm

  Xiao Yue, Bo Liu, Feng Zhang, Guangzhi Qu · 8 décembre 2025

  As a classical approach on graph learning, the propagation-aggregation methodology is widely exploited by many of Graph Neural Networks (GNNs), wherein the representation of a node is updated by aggregating representations from itself and neighbor nodes recursively. Similar to the propagation-aggreg…

• Bounded Graph Clustering with Graph Neural Networks

  Kibidi Neocosmos, Diego Baptista, Nicole Ludwig · 8 décembre 2025

  In community detection, many methods require the user to specify the number of clusters in advance since an exhaustive search over all possible values is computationally infeasible. While some classical algorithms can infer this number directly from the data, this is typically not the case for graph…

• Towards agent-based-model informed neural networks

  Nino Antulov-Fantulin · 8 décembre 2025

  In this article, we present a framework for designing neural networks that remain consistent with the underlying principles of agent-based models. We begin by highlighting the limitations of standard neural differential equations in modeling complex systems, where physical invariants (like energy) a…

• Causal LLM Routing: End-to-End Regret Minimization from Observational Data

  Asterios Tsiourvas, Wei Sun, Georgia Perakis · 4 décembre 2025

  LLM routing aims to select the most appropriate model for each query, balancing competing performance metrics such as accuracy and cost across a pool of language models. Prior approaches typically adopt a decoupled strategy, where the metrics are first predicted and the model is then selected based …