Advanced Graph Neural Networks

Derniers papiers

• Quasi-Equivariant Metanetworks

  Viet-Hoang Tran, An Nguyen, Beno\^it Gu\'erand, Thieu N. Vo, Tan M. Nguyen · 28 avril 2026

  Metanetworks are neural architectures designed to operate directly on pretrained weights to perform downstream tasks. However, the parameter space serves only as a proxy for the underlying function class, and the parameter-function mapping is inherently non-injective: distinct parameter configuratio…

• Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation

  Yuchen Yan, Peiyan Zhang, Zhihua Liu, Hao Wang, Yatao Bian, Weiming Li, Xiaoshuai Hao · 28 avril 2026

  Retrieval-augmented generation (RAG) has demonstrated its ability to enhance Large Language Models (LLMs) by integrating external knowledge sources. However, multi-hop questions, which require the identification of multiple knowledge targets to form a synthesized answer, raise new challenges for RAG…

• Hamiltonian Graph Inference Networks: Joint structure discovery and dynamics prediction for lattice Hamiltonian systems from trajectory data

  Ru Geng, Panayotis Kevrekidis, Yixian Gao, Hong-Kun Zhang, Jian Zu · 28 avril 2026

  Lattice Hamiltonian systems underpin models across condensed matter, nonlinear optics, and biophysics, yet learning their dynamics from data is obstructed by two unknowns: the interaction topology and whether node dynamics are homogeneous. Existing graph-based approaches either assume the graph is g…

• BiTA: Bidirectional Gated Recurrent Unit-Transformer Aggregator in a Temporal Graph Network Framework for Alert Prediction in Computer Networks

  Zahra Makki Nayeri, Mohsen Rezvani · 28 avril 2026

  Proactive alert prediction in computer networks is critical for mitigating evolving cyber threats and enabling timely defensive actions. Temporal Graph Neural Networks (TGNs) provide a principled framework for modeling time-evolving interactions; however, existing TGN-based methods predominantly rel…

• Scalable Production Scheduling: Linear Complexity via Unified Homogeneous Graphs

  Jonathan Hoss, Moritz Link, Noah Klarmann · 28 avril 2026

  Efficiently solving the Job Shop Scheduling Problem in real-world industrial applications requires policies that are both computationally lean and topologically robust. While Reinforcement Learning has shown potential in automating dispatching rules, existing models often struggle with a scalability…

• Gromov-Wasserstein Methods for Multi-View Relational Embedding and Clustering

  Rafael Pereira Eufrazio, Eduardo Fernandes Montesuma, Charles Casimiro Cavalcante · 28 avril 2026

  Learning low-dimensional representations from multi-view relational data is challenging when underlying geometries differ across views. We propose Bary-GWMDS, a Gromov-Wasserstein-based method that operates directly on distance matrices to learn a consensus embedding preserving shared relational str…

• LLM+Graph@VLDB'2025 Workshop Summary

  Yixiang Fang, Arijit Khan, Tianxing Wu, Da Yan, Shu Wang · 28 avril 2026

  The integration of large language models (LLMs) with graph-structured data has become a pivotal and fast evolving research frontier, drawing strong interest from both academia and industry. The 2nd LLM+Graph Workshop, co-located with the 51st International Conference on Very Large Data Bases (VLDB 2…

• Towards Understanding the Expressive Power of GNNs with Global Readout

  Maurice Funk, Daumantas Kojelis · 28 avril 2026

  We study the expressive power of message-passing aggregate-combine-readout graph neural networks (ACR-GNNs). Particularly, we focus on the first-order (FO) properties expressible by this formalism. While a tight logical characterisation remains a difficult open question, we make two contributions to…

• Layer Embedding Deep Fusion Graph Neural Network

  Taihua Xu, Genhao Tian, Jicong Fan, Xibei Yang, Qinghua Zhang, Yun Cui · 28 avril 2026

  Graph Neural Networks (GNNs) have demonstrated impressive performance in learning representations from graph-structured data. However, their message-passing mechanism inherently relies on the assumption of label consistency among connected nodes, limiting their applicability to low-homophily setting…

• Graph Memory Transformer (GMT)

  Nicola Zanarini, Niccol\`o Ferrari · 28 avril 2026

  We investigate whether the Feed-Forward Network (FFN) sublayer in a decoder-only transformer can be replaced by an explicit learned memory graph while preserving the surrounding autoregressive architecture. The proposed Graph Memory Transformer (GMT) keeps causal self-attention intact, but replaces …

• Latent-Hysteresis Graph ODEs: Modeling Coupled Topology-Feature Evolution via Continuous Phase Transitions

  Qinhan Hou, Jing Tang · 28 avril 2026

  Graph neural ordinary differential equations (Graph ODEs) extend graph learning from discrete message-passing layers to continuous-time representation flows. While it supports adaptive long-range propagation, we show that Graph ODEs with strictly positive irreducible mixing operators face an inheren…

• LLM+Graph@VLDB'2025 Workshop Summary

  Yixiang Fang, Arijit Khan, Tianxing Wu, Da Yan, Shu Wang · 27 avril 2026

  The integration of large language models (LLMs) with graph-structured data has become a pivotal and fast evolving research frontier, drawing strong interest from both academia and industry. The 2nd LLM+Graph Workshop, co-located with the 51st International Conference on Very Large Data Bases (VLDB 2…

• Operational Feature Fingerprints of Graph Datasets via a White-Box Signal-Subspace Probe

  Yuchen Xiong, Swee Keong Yeap, Zhen Hong Ban · 27 avril 2026

  Graph neural networks achieve strong node-classification accuracy, but their learned message passing entangles ego attributes, neighborhood smoothing, high-pass graph differences, class geometry, and classifier boundaries in an opaque representation. This obscures why a node is classified and what f…

• Mochi: Aligning Pre-training and Inference for Efficient Graph Foundation Models via Meta-Learning

  Jo\~ao Mattos, Arlei Silva · 27 avril 2026

  We propose Mochi, a Graph Foundation Model that addresses task unification and training efficiency by adopting a meta-learning based training framework. Prior models pre-train with reconstruction-based objectives such as link prediction, and assume that the resulting representations can be aligned w…

• Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control

  Qinhan Hou, Jing Tang · 27 avril 2026

  Graph Transformers can mix information globally, but this flexibility also creates failure modes: some tasks require long-range communication while others are better served by local interaction. We study this through a synthetic node-classification benchmark on contextual stochastic block model grap…

• Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization

  Shan He, Runze Wang, Zhuoyun Du, Huiyu Bai, Zouying Cao, Yu Cheng, Bo Zheng · 24 avril 2026

  Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat prompt tuning, lack the structural awareness to debug the intricate web of interactions in MAS. More critically, these o…

• Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction

  Thinh Nguyen-Cong, Truong-Son Hy, Thang N. Dinh · 24 avril 2026

  Graph Neural Networks (GNNs) excel on relational data, but standard benchmarks unrealistically assume the graph is centrally available. In practice, settings such as Federated Graph Learning, distributed systems, and privacy-sensitive applications involve graph data that are localized, fragmented, n…

• TRAVELFRAUDBENCH: A Configurable Evaluation Framework for GNN Fraud Ring Detection in Travel Networks

  Bhavana Sajja · 24 avril 2026

  We introduce TravelFraudBench (TFG), a configurable benchmark for evaluating graph neural networks (GNNs) on fraud ring detection in travel platform graphs. Existing benchmarks--YelpChi, Amazon-Fraud, Elliptic, PaySim--cover single node types or domain-generic patterns with no mechanism to evaluate …

• Graph Neural Network-Informed Predictive Flows for Faster Ford-Fulkerson and PAC-Learnability

  Eleanor Wiesler, Trace Baxley · 24 avril 2026

  We propose a learning-augmented framework for accelerating max-flow computation and image segmentation by integrating Graph Neural Networks (GNNs) with the Ford-Fulkerson algorithm. Rather than predicting initial flows, our method learns edge importance probabilities to guide augmenting path selecti…

• Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning

  Yuhan Peng, Junwen Dong, Yuzhi Zeng, Hao Li, Ce Ju, Huitao Feng, Diaaeldin Taha, Anna Wienhard, Kelin Xia · 23 avril 2026

  Graph neural networks face two fundamental challenges rooted in the linear structure of Euclidean vector spaces: (1) Current architectures represent geometry through vectors (directions, gradients), yet many tasks require matrix-valued representations that capture relationships between directions-su…

• Improved large-scale graph learning through ridge spectral sparsification

  Daniele Calandriello, Ioannis Koutis, Alessandro Lazaric, Michal Valko · 23 avril 2026

  Graph-based techniques and spectral graph theory have enriched the field of machine learning with a variety of critical advances. A central object in the analysis is the graph Laplacian L, which encodes the structure of the graph. We consider the problem of learning over this Laplacian in a distribu…

• F\textsuperscript{2}LP-AP: Fast \& Flexible Label Propagation with Adaptive Propagation Kernel

  Yutong Shen, Ruizhe Xia, Jingyi Liu, Yinqi Liu · 23 avril 2026

  Semi-supervised node classification is a foundational task in graph machine learning, yet state-of-the-art Graph Neural Networks (GNNs) are hindered by significant computational overhead and reliance on strong homophily assumptions. Traditional GNNs require expensive iterative training and multi-lay…

• Transformers Can Learn Connectivity in Some Graphs but Not Others

  Amit Roy, Abulhair Saparov · 23 avril 2026

  Reasoning capability is essential to ensure the factual correctness of the responses of transformer-based Large Language Models (LLMs), and robust reasoning about transitive relations is instrumental in many settings, such as causal inference. Hence, it is essential to investigate the capability of …

• When Graph Structure Becomes a Liability: A Critical Re-Evaluation of Graph Neural Networks for Bitcoin Fraud Detection under Temporal Distribution Shift

  Saket Maganti · 22 avril 2026

  The consensus that GCN, GraphSAGE, GAT, and EvolveGCN outperform feature-only baselines on the Elliptic Bitcoin Dataset is widely cited but has not been rigorously stress-tested under a leakage-free evaluation protocol. We perform a seed-matched inductive-versus-transductive comparison and find that…

• Reasoning Structure Matters for Safety Alignment of Reasoning Models

  Yeonjun In, Wonjoong Kim, Sangwu Park, Chanyoung Park · 22 avril 2026

  Large reasoning models (LRMs) achieve strong performance on complex reasoning tasks but often generate harmful responses to malicious user queries. This paper investigates the underlying cause of these safety risks and shows that the issue lies in the reasoning structure itself. Based on this insigh…