Advanced Graph Neural Networks

Derniers papiers

• Fully Inductive Node Representation Learning via Graph View Transformation

  Dooho Lee, Myeong Kong, Minho Jeong, Jaemin Yoo · 15 décembre 2025

  Generalizing a pretrained model to unseen datasets without retraining is an essential step toward a foundation model. However, achieving such cross-dataset, fully inductive inference is difficult in graph-structured data where feature spaces vary widely in both dimensionality and semantics. Any tran…

• Condensation-Concatenation Framework for Dynamic Graph Continual Learning

  Tingxu Yan, Ye Yuan · 15 décembre 2025

  Dynamic graphs are prevalent in real-world scenarios, where continuous structural changes induce catastrophic forgetting in graph neural networks (GNNs). While continual learning has been extended to dynamic graphs, existing methods overlook the effects of topological changes on existing nodes. To a…

• REDELEX: A Framework for Relational Deep Learning Exploration

  Jakub Pele\v{s}ka, Gustav \v{S}\'ir · 15 décembre 2025

  Relational databases (RDBs) are widely regarded as the gold standard for storing structured information. Consequently, predictive tasks leveraging this data format hold significant application promise. Recently, Relational Deep Learning (RDL) has emerged as a novel paradigm wherein RDBs are conceptu…

• Empowering GNNs for Domain Adaptation via Denoising Target Graph

  Haiyang Yu, Meng-Chieh Lee, Xiang song, Qi Zhu, Christos Faloutsos · 15 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…

• MedRule-KG: A Knowledge-Graph--Steered Scaffold for Mathematical Reasoning with a Lightweight Verifier

  Crystal Su · 15 décembre 2025

  Large language models (LLMs) often produce fluent reasoning steps while violating simple mathematical or logical constraints. We introduce MedRule-KG, a compact typed knowledge graph coupled with a symbolic verifier, designed to enforce mathematically interpretable rules in reasoning tasks. MedRule-…

• CAT: Can Trust be Predicted with Context-Awareness in Dynamic Heterogeneous Networks?

  Jie Wang, Zheng Yan, Jiahe Lan, Xuyan Li, Elisa Bertino · 15 décembre 2025

  Trust prediction provides valuable support for decision-making, risk mitigation, and system security enhancement. Recently, Graph Neural Networks (GNNs) have emerged as a promising approach for trust prediction, owing to their ability to learn expressive node representations that capture intricate t…

• GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism

  Sandeep Polisetty, Juelin Liu, Kobi Falus, Yi Ren Fung, Seung-Hwan Lim, Hui Guan, Marco Serafini · 15 décembre 2025

  Graph neural networks (GNNs), an emerging class of machine learning models for graphs, have gained popularity for their superior performance in various graph analytical tasks. Mini-batch training is commonly used to train GNNs on large graphs, and data parallelism is the standard approach to scale m…

• LGAN: An Efficient High-Order Graph Neural Network via the Line Graph Aggregation

  Lin Du, Lu Bai, Jincheng Li, Lixin Cui, Hangyuan Du, Lichi Zhang, Yuting Chen, Zhao Li · 12 décembre 2025

  Graph Neural Networks (GNNs) have emerged as a dominant paradigm for graph classification. Specifically, most existing GNNs mainly rely on the message passing strategy between neighbor nodes, where the expressivity is limited by the 1-dimensional Weisfeiler-Lehman (1-WL) test. Although a number of k…

• GT-SNT: A Linear-Time Transformer for Large-Scale Graphs via Spiking Node Tokenization

  Huizhe Zhang, Jintang Li, Yuchang Zhu, Huazhen Zhong, Liang Chen · 12 décembre 2025

  Graph Transformers (GTs), which integrate message passing and self-attention mechanisms simultaneously, have achieved promising empirical results in graph prediction tasks. However, the design of scalable and topology-aware node tokenization has lagged behind other modalities. This gap becomes criti…

• Multi-Granular Node Pruning for Circuit Discovery

  Muhammad Umair Haider, Hammad Rizwan, Hassan Sajjad, A. B. Siddique · 12 décembre 2025

  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…

• HGC-Herd: Efficient Heterogeneous Graph Condensation via Representative Node Herding

  Fuyan Ou, Siqi Ai, Yulin Hu · 12 décembre 2025

  Heterogeneous graph neural networks (HGNNs) have demonstrated strong capability in modeling complex semantics across multi-type nodes and relations. However, their scalability to large-scale graphs remains challenging due to structural redundancy and high-dimensional node features. Existing graph co…

• RoFt-Mol: Benchmarking Robust Fine-Tuning with Molecular Graph Foundation Models

  Shikun Liu, Deyu Zou, Nima Shoghi, Victor Fung, Kai Liu, Pan Li · 12 décembre 2025

  In the era of foundation models, fine-tuning pre-trained models for specific downstream tasks has become crucial. This drives the need for robust fine-tuning methods to address challenges such as model overfitting and sparse labeling. Molecular graph foundation models (MGFMs) face unique difficultie…

• THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation

  Ming-Yi Hong, Miao-Chen Chiang, Youchen Teng, Yu-Hsiang Wang, Chih-Yu Wang, Che Lin · 12 décembre 2025

  Heterogeneous Graph Neural Networks (HGNNs) are effective for modeling Heterogeneous Information Networks (HINs), which encode complex multi-typed entities and relations. However, HGNNs often suffer from type information loss and structural noise, limiting their representational fidelity and general…

• Representation of the structure of graphs by sequences of instructions

  Ezequiel Lopez-Rubio · 12 décembre 2025

  The representation of graphs is commonly based on the adjacency matrix concept. This formulation is the foundation of most algebraic and computational approaches to graph processing. The advent of deep learning language models offers a wide range of powerful computational models that are specialized…

• Analysis of Dirichlet Energies as Over-smoothing Measures

  Anna Bison, Alessandro Sperduti · 11 décembre 2025

  We analyze the distinctions between two functionals often used as over-smoothing measures: the Dirichlet energies induced by the unnormalized graph Laplacian and the normalized graph Laplacian. We demonstrate that the latter fails to satisfy the axiomatic definition of a node-similarity measure prop…

• LLMs for Analog Circuit Design Continuum (ACDC)

  Yasaman Esfandiari, Jocelyn Rego, Austin Meyer, Jonathan Gallagher, Mia Levy · 11 décembre 2025

  Large Language Models (LLMs) and transformer architectures have shown impressive reasoning and generation capabilities across diverse natural language tasks. However, their reliability and robustness in real-world engineering domains remain largely unexplored, limiting their practical utility in hum…

• Branching Strategies Based on Subgraph GNNs: A Study on Theoretical Promise versus Practical Reality

  Junru Zhou, Yicheng Wang, Pan Li · 11 décembre 2025

  Graph Neural Networks (GNNs) have emerged as a promising approach for ``learning to branch'' in Mixed-Integer Linear Programming (MILP). While standard Message-Passing GNNs (MPNNs) are efficient, they theoretically lack the expressive power to fully represent MILP structures. Conversely, higher-orde…

• Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power

  Yuzhu Chen, Tian Qin, Xinmei Tian, Fengxiang He, Dacheng Tao · 11 décembre 2025

  Equivariant neural networks encode symmetry as an inductive bias and have achieved strong empirical performance in wide domains. However, their expressive power remains not well understood. Focusing on 2-layer ReLU networks, this paper investigates the impact of equivariance constraints on the expre…

• PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models

  Yu Liu, Xixun Lin, Yanmin Shang, Yangxi Li, Shi Wang, Yanan Cao · 11 décembre 2025

  Knowledge graph reasoning (KGR) is the task of inferring new knowledge by performing logical deductions on knowledge graphs. Recently, large language models (LLMs) have demonstrated remarkable performance in complex reasoning tasks. Despite promising success, current LLM-based KGR methods still face…

• SEA: Spectral Edge Attacks on Graph Neural Networks

  Yongyu Wang · 11 décembre 2025

  Graph Neural Networks (GNNs) achieve strong performance on graph-structured data, but are notoriously vulnerable to small, carefully crafted perturbations of the graph structure. Most existing structure-based attacks rely on gradient-based heuristics or local connectivity patterns, and treat edges a…

• Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks

  Hunjae Lee · 11 décembre 2025

  Transformers and more specifically decoder-only transformers dominate modern LLM architectures. While they have shown to work exceptionally well, they are not without issues, resulting in surprising failure modes and predictably asymmetric performance degradation. This article is a study of many of …

• Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment

  Shanghao Li, Jinda Han, Yibo Wang, Yuanjie Zhu, Zihe Song, Langzhou He, Kenan Kamel A Alghythee, Philip S. Yu · 11 décembre 2025

  Graph-based Retrieval-Augmented Generation (GraphRAG) enhances Large Language Models (LLMs) by incorporating external knowledge from linearized subgraphs retrieved from knowledge graphs. However, LLMs struggle to interpret the relational and topological information in these inputs, resulting in hall…

• Incorporating Fairness in Neighborhood Graphs for Fair Spectral Clustering

  Adithya K Moorthy, V Vijaya Saradhi, Bhanu Prasad · 11 décembre 2025

  Graph clustering plays a pivotal role in unsupervised learning methods like spectral clustering, yet traditional methods for graph clustering often perpetuate bias through unfair graph constructions that may underrepresent some groups. The current research introduces novel approaches for constructin…

• BG-HGNN: Toward Efficient Learning for Complex Heterogeneous Graphs

  Junwei Su, Lingjun Mao, Zheng Da, Chuan Wu · 10 décembre 2025

  Heterogeneous graphs, comprising diverse node and edge types connected through varied relations, are ubiquitous in real-world applications. Message-passing heterogeneous graph neural networks (HGNNs) have emerged as a powerful model class for such data. However, existing HGNNs typically allocate a s…

• GLL: A Differentiable Graph Learning Layer for Neural Networks

  Jason Brown, Bohan Chen, Harris Hardiman-Mostow, Jeff Calder, Andrea L. Bertozzi · 10 décembre 2025

  Standard deep learning architectures used for classification generate label predictions with a projection head and softmax activation function. Although successful, these methods fail to leverage the relational information between samples for generating label predictions. In recent works, graph-base…