Advanced Graph Neural Networks

Derniers papiers

• HiGen: Hierarchical Graph Generative Networks

  Mahdi Karami · 1 janvier 2026

  Most real-world graphs exhibit a hierarchical structure, which is often overlooked by existing graph generation methods. To address this limitation, we propose a novel graph generative network that captures the hierarchical nature of graphs and successively generates the graph sub-structures in a co…

• Hyperspherical Graph Representation Learning via Adaptive Neighbor-Mean Alignment and Uniformity

  Rui Chen, Junjun Guo, Hongbin Wang, Yan Xiang, Yantuan Xian, Zhengtao Yu · 1 janvier 2026

  Graph representation learning (GRL) aims to encode structural and semantic dependencies of graph-structured data into low-dimensional embeddings. However, existing GRL methods often rely on surrogate contrastive objectives or mutual information maximization, which typically demand complex architectu…

• mHC: Manifold-Constrained Hyper-Connections

  Zhenda Xie, Yixuan Wei, Huanqi Cao, Chenggang Zhao, Chengqi Deng, Jiashi Li, Damai Dai, Huazuo Gao, Jiang Chang, Liang Zhao, Shangyan Zhou, Zhean Xu, Zhengyan Zhang, Wangding Zeng, Shengding Hu, Yuqing Wang, Jingyang Yuan, Lean Wang, Wenfeng Liang · 1 janvier 2026

  Recently, studies exemplified by Hyper-Connections (HC) have extended the ubiquitous residual connection paradigm established over the past decade by expanding the residual stream width and diversifying connectivity patterns. While yielding substantial performance gains, this diversification fundame…

• Learning Network Dismantling Without Handcrafted Inputs

  Haozhe Tian, Pietro Ferraro, Robert Shorten, Mahdi Jalili, Homayoun Hamedmoghadam · 1 janvier 2026

  The application of message-passing Graph Neural Networks has been a breakthrough for important network science problems. However, the competitive performance often relies on using handcrafted structural features as inputs, which increases computational cost and introduces bias into the otherwise pur…

• HeteroHBA: A Generative Structure-Manipulating Backdoor Attack on Heterogeneous Graphs

  Honglin Gao, Lan Zhao, Junhao Ren, Xiang Li, Gaoxi Xiao · 1 janvier 2026

  Heterogeneous graph neural networks (HGNNs) have achieved strong performance in many real-world applications, yet targeted backdoor poisoning on heterogeneous graphs remains less studied. We consider backdoor attacks for heterogeneous node classification, where an adversary injects a small set of tr…

• Adjusted Count Quantification Learning on Graphs

  Clemens Damke, Eyke H\"ullermeier · 1 janvier 2026

  Quantification learning is the task of predicting the label distribution of a set of instances. We study this problem in the context of graph-structured data, where the instances are vertices. Previously, this problem has only been addressed via node clustering methods. In this paper, we extend the …

• Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks

  Maksim Kryzhanovskiy, Svetlana Glazyrina, Roman Ischenko, Konstantin Vorontsov · 30 décembre 2025

  Modern AI systems often comprise multiple learnable components that can be naturally organized as graphs. A central challenge is the end-to-end training of such systems without restrictive architectural or training assumptions. Such tasks fit the theory and approaches of the collaborative Multi-Agen…

• GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphs

  Enjun Du, Siyi Liu, Yongqi Zhang · 30 décembre 2025

  Knowledge graph reasoning in the fully-inductive setting, where both entities and relations at test time are unseen during training, remains an open challenge. In this work, we introduce GraphOracle, a novel framework that achieves robust fully-inductive reasoning by transforming each knowledge grap…

• Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses

  Yongyu Wang · 30 décembre 2025

  Graph Neural Networks (GNNs) have emerged as a dominant paradigm for learning on graph-structured data, thanks to their ability to jointly exploit node features and relational information encoded in the graph topology. This joint modeling, however, also introduces a critical weakness: perturbations …

• Interpretable and Adaptive Node Classification on Heterophilic Graphs via Combinatorial Scoring and Hybrid Learning

  Soroush Vahidi · 30 décembre 2025

  Graph neural networks (GNNs) achieve strong performance on homophilic graphs but often struggle under heterophily, where adjacent nodes frequently belong to different classes. We propose an interpretable and adaptive framework for semi-supervised node classification based on explicit combinatorial i…

• Transformer Reconstructed with Dynamic Value Attention

  Xiaowei Wang · 30 décembre 2025

  Since transformer was firstly published in 2017, several works have been proposed to optimize it. However, the major structure of transformer remains unchanged, ignoring one of its main intrinsic limitations, which is the same static value is used for every query in a head. Transformer itself tries …

• The Gaining Paths to Investment Success: Information-Driven LLM Graph Reasoning for Venture Capital Prediction

  Haoyu Pei, Zhongyang Liu, Xiangyi Xiao, Xiaocong Du, Haipeng Zhang, Kunpeng Zhang, Suting Hong · 30 décembre 2025

  Most venture capital (VC) investments fail, while a few deliver outsized returns. Accurately predicting startup success requires synthesizing complex relational evidence, including company disclosures, investor track records, and investment network structures, through explicit reasoning to form cohe…

• Decomposing Uncertainty in Probabilistic Knowledge Graph Embeddings: Why Entity Variance Is Not Enough

  Chorok Lee · 30 décembre 2025

  Probabilistic knowledge graph embeddings represent entities as distributions, using learned variances to quantify epistemic uncertainty. We identify a fundamental limitation: these variances are relation-agnostic, meaning an entity receives identical uncertainty regardless of relational context. Thi…

• GRExplainer: A Universal Explanation Method for Temporal Graph Neural Networks

  Xuyan Li, Jie Wang, Zheng Yan · 30 décembre 2025

  Dynamic graphs are widely used to represent evolving real-world networks. Temporal Graph Neural Networks (TGNNs) have emerged as a powerful tool for processing such graphs, but the lack of transparency and explainability limits their practical adoption. Research on TGNN explainability is still in it…

• LLMTM: Benchmarking and Optimizing LLMs for Temporal Motif Analysis in Dynamic Graphs

  Bing Hao, Minglai Shao, Zengyi Wo, Yunlong Chu, Yuhang Liu, Ruijie Wang · 30 décembre 2025

  The widespread application of Large Language Models (LLMs) has motivated a growing interest in their capacity for processing dynamic graphs. Temporal motifs, as an elementary unit and important local property of dynamic graphs which can directly reflect anomalies and unique phenomena, are essential …

• Multi-Head Spectral-Adaptive Graph Anomaly Detection

  Qingyue Cao, Bo Jin, Changwei Gong, Xin Tong, Wenzheng Li, Xiaodong Zhou · 30 décembre 2025

  Graph anomaly detection technology has broad applications in financial fraud and risk control. However, existing graph anomaly detection methods often face significant challenges when dealing with complex and variable abnormal patterns, as anomalous nodes are often disguised and mixed with normal no…

• BLISS: Bandit Layer Importance Sampling Strategy for Efficient Training of Graph Neural Networks

  Omar Alsaqa, Linh Thi Hoang, Muhammed Fatih Balin · 30 décembre 2025

  Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their application to large graphs is hindered by computational costs. The need to process every neighbor for each node creates memory and computational bottlenecks. To address this, we introduce BLISS, a Ban…

• Graph Attention-based Adaptive Transfer Learning for Link Prediction

  Huashen Lu, Wensheng Gan, Guoting Chen, Zhichao Huang, Philip S. Yu · 30 décembre 2025

  Graph neural networks (GNNs) have brought revolutionary advancements to the field of link prediction (LP), providing powerful tools for mining potential relationships in graphs. However, existing methods face challenges when dealing with large-scale sparse graphs and the need for a high degree of al…

• Task-driven Heterophilic Graph Structure Learning

  Ayushman Raghuvanshi, Gonzalo Mateos, Sundeep Prabhakar Chepuri · 30 décembre 2025

  Graph neural networks (GNNs) often struggle to learn discriminative node representations for heterophilic graphs, where connected nodes tend to have dissimilar labels and feature similarity provides weak structural cues. We propose frequency-guided graph structure learning (FgGSL), an end-to-end gra…

• Geometric Structural Knowledge Graph Foundation Model

  Ling Xin, Mojtaba Nayyeri, Zahra Makki Nayeri, Steffen Staab · 30 décembre 2025

  Structural knowledge graph foundation models aim to generalize reasoning to completely new graphs with unseen entities and relations. A key limitation of existing approaches like Ultra is their reliance on a single relational transformation (e.g., element-wise multiplication) in message passing, whi…

• DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation

  Shiyan Liu, Jian Ma, Rui Qu · 30 décembre 2025

  As Retrieval-Augmented Generation (RAG) systems evolve toward more sophisticated architectures, ensuring their trustworthiness through explainable and robust evaluation becomes critical. Existing scalar metrics suffer from limited interpretability, inadequate uncertainty quantification, and computat…

• Lightweight Inference-Time Personalization for Frozen Knowledge Graph Embeddings

  Ozan Oguztuzun, Cerag Oguztuzun · 30 décembre 2025

  Foundation models for knowledge graphs (KGs) achieve strong cohort-level performance in link prediction, yet fail to capture individual user preferences; a key disconnect between general relational reasoning and personalized ranking. We propose GatedBias, a lightweight inference-time personalization…

• GINTRIP: Interpretable Temporal Graph Regression using Information bottleneck and Prototype-based method

  Ali Royat, Seyed Mohamad Moghadas, Lesley De Cruz, Adrian Munteanu · 30 décembre 2025

  Deep neural networks (DNNs) have demonstrated remarkable performance across various domains, but their inherent complexity makes them challenging to interpret. This is especially true for temporal graph regression tasks due to the complex underlying spatio-temporal patterns in the graph. While inter…

• AnchorGK: Anchor-based Incremental and Stratified Graph Learning Framework for Inductive Spatio-Temporal Kriging

  Xiaobin Ren, Kaiqi Zhao, Katerina Ta\v{s}kova, Patricia Riddle · 29 décembre 2025

  Spatio-temporal kriging is a fundamental problem in sensor networks, driven by the sparsity of deployed sensors and the resulting missing observations. Although recent approaches model spatial and temporal correlations, they often under-exploit two practical characteristics of real deployments: the …

• HWL-HIN: A Hypergraph-Level Hypergraph Isomorphism Network as Powerful as the Hypergraph Weisfeiler-Lehman Test with Application to Higher-Order Network Robustness

  Chengyu Tian, Wenbin Pei · 29 décembre 2025

  Robustness in complex systems is of significant engineering and economic importance. However, conventional attack-based a posteriori robustness assessments incur prohibitive computational overhead. Recently, deep learning methods, such as Convolutional Neural Networks (CNNs) and Graph Neural Network…