Advanced Graph Neural Networks

Derniers papiers

• Scalable and Adaptive Parallel Training of Graph Transformer on Large Graphs

  Jun-Liang Lin, Kamesh Madduri, Mahmut Taylan Kandemir · 21 avril 2026

  Graph foundation models have demonstrated remarkable adaptability across diverse downstream tasks through large-scale pretraining on graphs. However, existing implementations of the backbone model, graph transformers, are typically limited to single-GPU systems, leading to long training times or out…

• Geodesic Semantic Search: Cartographic Navigation of Citation Graphs with Learned Local Riemannian Maps

  Brandon Yee, Lucas Wang, Kundana Kommini, Krishna Sharma · 21 avril 2026

  We present Geodesic Semantic Search (GSS), a retrieval system that learns node-specific Riemannian metrics on citation graphs to enable geometry-aware semantic search. Unlike standard embedding-based retrieval that relies on fixed Euclidean distances, \gss{} learns a low-rank metric tensor $\mL_i \i…

• Semantic-based Distributed Learning for Diverse and Discriminative Representations

  Zhuojun Tian, Chaouki Ben Issaid, Mehdi Bennis · 21 avril 2026

  In large-scale distributed scenarios, increasingly complex tasks demand more intelligent collaboration across networks, requiring the joint extraction of structural representations from data samples. However, conventional task-specific approaches often result in nonstructural embeddings, leading to …

• Federation over Text: Insight Sharing for Multi-Agent Reasoning

  Dixi Yao, Tahseen Rabbani, Tian Li · 21 avril 2026

  LLM-powered agents often reason from scratch when presented with a new problem instance and lack automatic mechanisms to transfer learned skills to other agents. We propose a federated learning-like framework, Federation over Text (FoT), that enables multiple agents solving different tasks to collec…

• Generalization Boundaries of Fine-Tuned Small Language Models for Graph Structural Inference

  Michal Podstawski · 21 avril 2026

  Small language models fine-tuned for graph property estimation have demonstrated strong in-distribution performance, yet their generalization capabilities beyond training conditions remain poorly understood. In this work, we systematically investigate the boundaries of structural inference in fine-t…

• On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks

  Mingsong Yan, Charles Kulick, Sui Tang · 21 avril 2026

  Continuous-depth graph neural networks, also known as Graph Neural Differential Equations (GNDEs), combine the structural inductive bias of Graph Neural Networks (GNNs) with the continuous-depth architecture of Neural ODEs, offering a scalable and principled framework for modeling dynamics on graphs…

• Graph Neural Networks for Graphs with Heterophily: A Survey

  Xin Zheng, Yi Wang, Yixin Liu, Ming Li, Miao Zhang, Di Jin, Philip S. Yu, Shirui Pan · 21 avril 2026

  Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriad graph analytic tasks and applications. Most GNNs rely on the homophily assumption that nodes belonging to the same class are more likely to be connected. However, as a ubiquitous graph property i…

• SigGate-GT: Taming Over-Smoothing in Graph Transformers via Sigmoid-Gated Attention

  Dongxin Guo, Jikun Wu, Siu Ming Yiu · 21 avril 2026

  Graph transformers achieve strong results on molecular and long-range reasoning tasks, yet remain hampered by over-smoothing (the progressive collapse of node representations with depth) and attention entropy degeneration. We observe that these pathologies share a root cause with attention sinks in …

• Torch Geometric Pool: the PyTorch library for pooling in Graph Neural Networks

  Carlo Abate, Ivan Marisca, Filippo Maria Bianchi · 21 avril 2026

  Torch Geometric Pool (tgp) is a pooling library built on top of PyTorch Geometric. Graph pooling methods differ in how they assign nodes to supernodes, how they handle batches, what they return after pooling, and whether they expose auxiliary losses. These differences make it hard to compare methods…

• LoReC: Rethinking Large Language Models for Graph Data Analysis

  Hongyu Zhan, Qixin Wang, Yusen Tan, Haitao Yu, Jingbo Zhou, Shuai Chen, Jia Li, Xiao Tan, Jun Xia · 21 avril 2026

  The advent of Large Language Models (LLMs) has fundamentally reshaped the way we interact with graphs, giving rise to a new paradigm called GraphLLM. As revealed in recent studies, graph learning can benefit from LLMs. However, we observe limited benefits when we directly utilize LLMs to make predic…

• Dynamic Sheaf Diffusion Networks with Adaptive Local Structure for Heterogeneous Spatio-Temporal Graph Learning

  Abeer Mostafa, Raneen Younis, Zahra Ahmadi · 21 avril 2026

  Spatio-temporal processes often exhibit highly heterogeneous and non-intuitive responses to localized disruptions, limiting the effectiveness of conventional message passing approaches in modeling local heterogeneity. We reformulate spatio-temporal forecasting as the problem of learning information …

• Do LLM-derived graph priors improve multi-agent coordination?

  Nikunj Gupta, Rajgopal Kannan, Viktor Prasanna · 21 avril 2026

  Multi-agent reinforcement learning (MARL) is crucial for AI systems that operate collaboratively in distributed and adversarial settings, particularly in multi-domain operations (MDO). A central challenge in cooperative MARL is determining how agents should coordinate: existing approaches must eithe…

• TopFeaRe: Locating Critical State of Adversarial Resilience for Graphs Regarding Topology-Feature Entanglement

  Xinxin Fan, Wenxiong Chen, Quanliang Jing, Chi Lin, Shaoye Luo, Wenbo Song, Yunfeng Lu · 20 avril 2026

  Graph adversarial attacks are usually produced from the two perspectives of topology/structure and node feature, both of them represent the paramount characteristics learned by today's deep learning models. Although some defense countermeasures are proposed at present, they fails to disclose the int…

• Graph self-supervised learning based on frequency corruption

  Haojie Li, Mengjiao Zhang, Guanfeng Liu, Qiang Hu, Yan Wang, Junwei Du · 20 avril 2026

  Graph self-supervised learning can reduce the need for labeled graph data and has been widely used in recommendation, social networks, and other web applications. However, existing methods often underuse high-frequency signals and may overfit to specific local patterns, which limits representation q…

• Adaptive Spatio-temporal Estimation on the Graph Edges via Line Graph Transformation

  Yi Yan, Ercan Engin Kuruoglu · 20 avril 2026

  Spatial-temporal estimation of signals on graph edges is challenging because most conventional Graph Signal Processing techniques are defined on the graph nodes. Leveraging the Line Graph transform, the Line Graph Least Mean Square (LGLMS) algorithm unifies the Line Graph transformation with classic…

• NK-GAD: Neighbor Knowledge-Enhanced Unsupervised Graph Anomaly Detection

  Zehao Wang, Lanjun Wang · 20 avril 2026

  Graph anomaly detection aims to identify irregular patterns in graph-structured data. Most unsupervised GNN-based methods rely on the homophily assumption that connected nodes share similar attributes. However, real-world graphs often exhibit attribute-level heterophily, where connected nodes have d…

• Graph-Based Fraud Detection with Dual-Path Graph Filtering

  Wei He, Wensheng Gan, Philip S. Yu · 17 avril 2026

  Fraud detection on graph data can be viewed as a demanding task that requires distinguishing between different types of nodes. Because graph neural networks (GNNs) are naturally suited for processing information encoded in graph form through their message-passing operations, methods based on GNN mod…

• Cosine-Similarity Routing with Semantic Anchors for Interpretable Mixture-of-Experts Language Models

  Ivan Ternovtsii, Yurii Bilak · 17 avril 2026

  Mixture-of-Experts (MoE) models improve efficiency through sparse activation, but their learned gating functions provide limited insight into routing decisions. This work introduces the Semantic Resonance Architecture (SRA), which routes tokens to experts via cosine similarity between token represen…

• Disentangle-then-Refine: LLM-Guided Decoupling and Structure-Aware Refinement for Graph Contrastive Learning

  Zhaoxing Li, Hai-Feng Zhang, Xiaoming Zhang · 17 avril 2026

  Conventional Graph Contrastive Learning (GCL) on Text-Attributed Graphs (TAGs) relies on blind stochastic augmentations, inadvertently entangling task-relevant signals with noise. We propose SDM-SCR, a robust framework anchored in Approximate Orthogonal Decomposition. First, the Semantic Decoupling …

• Ollivier-Ricci Curvature of Riemannian Manifolds and Directed Graphs with Applications to Graph Neural Networks

  Eleanor Wiesler · 17 avril 2026

  This thesis is an exposition of Ollivier-Ricci Curvature of metric spaces as introduced by Yann Ollivier, which is based upon the 1-Wasserstein Distance and optimal transport theory. We present some of the major results and proofs that connect Ollivier-Ricci curvature with classical Ricci curvature …

• Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks

  Zhaobo Hu, Vincent Gauthier, Mehdi Naima · 17 avril 2026

  Graph Neural Networks (GNNs) conventionally rely on standard Laplacian or adjacency matrices for structural message passing. In this work, we substitute the traditional Laplacian with a Doubly Stochastic graph Matrix (DSM), derived from the inverse of the modified Laplacian, to naturally encode cont…

• Knowledge Graph RAG: Agentic Crawling and Graph Construction in Enterprise Documents

  Koushik Chakraborty, Koyel Guha · 17 avril 2026

  This research paper addresses the limitations of semantic search in complex enterprise document ecosystems. Traditional RAG pipelines often fail to capture hierarchical and interconnected information, leading to retrieval inaccuracies. We propose Agentic Knowledge Graphs featuring Recursive Crawling…

• Unsupervised Learning of Local Updates for Maximum Independent Set in Dynamic Graphs

  Devendra Parkar, Anya Chaturvedi, Joshua J. Daymude · 17 avril 2026

  We present the first unsupervised learning model for Maximum-Independent-Set (MaxIS) in dynamic graphs where edges change over time. Our method combines structural learning from graph neural networks (GNNs) with a learned distributed update mechanism that, given an edge addition or deletion event, m…

• Equifinality in Mixture of Experts: Routing Topology Does Not Determine Language Modeling Quality

  Ivan Ternovtsii, Yurii Bilak · 17 avril 2026

  Sparse Mixture-of-Experts (MoE) architectures employ increasingly sophisticated routing mechanisms -- learned routers, multi-hop trajectories, token-dependent gating. We ask: does routing topology actually determine language modeling quality? We build a geometric MoE (ST-MoE) using cosine-similarity…

• How Embeddings Shape Graph Neural Networks: Classical vs Quantum-Oriented Node Representations

  Nouhaila Innan, Antonello Rosato, Alberto Marchisio, Muhammad Shafique · 17 avril 2026

  Node embeddings act as the information interface for graph neural networks, yet their empirical impact is often reported under mismatched backbones, splits, and training budgets. This paper provides a controlled benchmark of embedding choices for graph classification, comparing classical baselines w…