Advanced Graph Neural Networks

Derniers papiers

• Angular Graph Fractional Fourier Transform: Theory and Application

  Feiyue Zhao, Yangfan He, Zhichao Zhang · 21 novembre 2025

  Graph spectral representations are fundamental in graph signal processing, offering a rigorous framework for analyzing and processing graph-structured data. The graph fractional Fourier transform (GFRFT) extends the classical graph Fourier transform (GFT) with a fractional-order parameter, enabling …

• Multi-dimensional Data Analysis and Applications Basing on LLM Agents and Knowledge Graph Interactions

  Xi Wang, Xianyao Ling, Kun Li, Gang Yin, Liang Zhang, Jiang Wu, Jun Xu, Fu Zhang, Wenbo Lei, Annie Wang, Peng Gong · 21 novembre 2025

  In the current era of big data, extracting deep insights from massive, heterogeneous, and complexly associated multi-dimensional data has become a significant challenge. Large Language Models (LLMs) perform well in natural language understanding and generation, but still suffer from "hallucination" …

• Graph-Memoized Reasoning: Foundations Structured Workflow Reuse in Intelligent Systems

  Yash Raj Singh · 21 novembre 2025

  Modern large language model-based reasoning systems frequently recompute similar reasoning steps across tasks, wasting computational resources, inflating inference latency, and limiting reproducibility. These inefficiencies underscore the need for persistent reasoning mechanisms that can recall and …

• MUSEKG: A Knowledge Graph Over Museum Collections

  Jinhao Li, Jianzhong Qi, Soyeon Caren Han, Eun-Jung Holden · 21 novembre 2025

  Digital transformation in the cultural heritage sector has produced vast yet fragmented collections of artefact data. Existing frameworks for museum information systems struggle to integrate heterogeneous metadata, unstructured documents, and multimodal artefacts into a coherent and queryable form. …

• Graph Diffusion Counterfactual Explanation

  David Bechtoldt, Sidney Bender · 21 novembre 2025

  Machine learning models that operate on graph-structured data, such as molecular graphs or social networks, often make accurate predictions but offer little insight into why certain predictions are made. Counterfactual explanations address this challenge by seeking the closest alternative scenario w…

• HybSpecNet: A Critical Analysis of Architectural Instability in Hybrid-Domain Spectral GNNs

  Huseyin Goksu · 21 novembre 2025

  Spectral Graph Neural Networks offer a principled approach to graph filtering but face a fundamental "Stability-vs-Adaptivity" trade-off. This trade-off is dictated by the choice of spectral domain. Filters in the finite [-1, 1] domain (e.g., ChebyNet) are numerically stable at high polynomial degre…

• Gauge-Equivariant Graph Networks via Self-Interference Cancellation

  Yoonhyuk Choi, Chong-Kwon Kim · 21 novembre 2025

  Graph Neural Networks (GNNs) excel on homophilous graphs but often fail under heterophily due to self-reinforcing and phase-inconsistent signals. We propose a Gauge-Equivariant Graph Network with Self-Interference Cancellation (GESC), which replaces additive aggregation with a projection-based inter…

• KrawtchoukNet: A Unified GNN Solution for Heterophily and Over-smoothing with Adaptive Bounded Polynomials

  Huseyin Goksu · 20 novembre 2025

  Spectral Graph Neural Networks (GNNs) based on polynomial filters, such as ChebyNet, suffer from two critical limitations: 1) performance collapse on "heterophilic" graphs and 2) performance collapse at high polynomial degrees (K), known as over-smoothing. Both issues stem from the static, low-pass …

• LaguerreNet: Advancing a Unified Solution for Heterophily and Over-smoothing with Adaptive Continuous Polynomials

  Huseyin Goksu · 20 novembre 2025

  Spectral Graph Neural Networks (GNNs) suffer from two critical limitations: poor performance on "heterophilic" graphs and performance collapse at high polynomial degrees (K), known as over-smoothing. Both issues stem from the static, low-pass nature of standard filters (e.g., ChebyNet). While adapti…

• Knowledge Graphs as Structured Memory for Embedding Spaces: From Training Clusters to Explainable Inference

  Artur A. Oliveira, Mateus Espadoto, Roberto M. Cesar Jr., Roberto Hirata Jr · 20 novembre 2025

  We introduce Graph Memory (GM), a structured non-parametric framework that augments embedding-based inference with a compact, relational memory over region-level prototypes. Rather than treating each training instance in isolation, GM summarizes the embedding space into prototype nodes annotated wit…

• DualLaguerreNet: A Decoupled Spectral Filter GNN and the Uncovering of the Flexibility-Stability Trade-off

  Huseyin Goksu · 19 novembre 2025

  Graph Neural Networks (GNNs) based on spectral filters, such as the Adaptive Orthogonal Polynomial Filter (AOPF) class (e.g., LaguerreNet), have shown promise in unifying the solutions for heterophily and over-smoothing. However, these single-filter models suffer from a "compromise" problem, as thei…

• A Survey of Cross-domain Graph Learning: Progress and Future Directions

  Haihong Zhao, Zhixun Li, Chenyi Zi, Aochuan Chen, Fugee Tsung, Jia Li, Jeffrey Xu Yu · 19 novembre 2025

  Graph learning plays a vital role in mining and analyzing complex relationships within graph data and has been widely applied to real-world scenarios such as social, citation, and e-commerce networks. Foundation models in computer vision (CV) and natural language processing (NLP) have demonstrated r…

• Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion

  Cristina L\'opez Amado, Tassilo Schwarz, Yu Tian, Renaud Lambiotte · 19 novembre 2025

  Graph Neural Networks (GNNs) have achieved remarkable success across diverse applications, yet they remain limited by oversmoothing and poor performance on heterophilic graphs. To address these challenges, we introduce a novel framework that equips graphs with a complex-weighted structure, assigning…

• Certified Signed Graph Unlearning

  Junpeng Zhao, Lin Li, Kaixi Hu, Kaize Shi, Jingling Yuan · 19 novembre 2025

  Signed graphs model complex relationships through positive and negative edges, with widespread real-world applications. Given the sensitive nature of such data, selective removal mechanisms have become essential for privacy protection. While graph unlearning enables the removal of specific data infl…

• Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning

  F\'elix Lefebvre, Ga\"el Varoquaux · 19 novembre 2025

  Many machine learning tasks can benefit from external knowledge. Large knowledge graphs store such knowledge, and embedding methods can be used to distill it into ready-to-use vector representations for downstream applications. For this purpose, current models have however two limitations: they are …

• GegenbauerNet: Finding the Optimal Compromise in the GNN Flexibility-Stability Trade-off

  Huseyin Goksu · 19 novembre 2025

  Spectral Graph Neural Networks (GNNs) operating in the canonical [-1, 1] domain (like ChebyNet and its adaptive generalization, L-JacobiNet) face a fundamental Flexibility-Stability Trade-off. Our previous work revealed a critical puzzle: the 2-parameter adaptive L-JacobiNet often suffered from high…

• Self-Adaptive Graph Mixture of Models

  Mohit Meena (Fujitsu Research of India, Bangalore), Yash Punjabi (Fujitsu Research of India, Bangalore), Abhishek A (Fujitsu Research of India, Bangalore), Vishal Sharma (Fujitsu Research of India, Bangalore), Mahesh Chandran (Fujitsu Research of India, Bangalore) · 18 novembre 2025

  Graph Neural Networks (GNNs) have emerged as powerful tools for learning over graph-structured data, yet recent studies have shown that their performance gains are beginning to plateau. In many cases, well-established models such as GCN and GAT, when appropriately tuned, can match or even exceed the…

• Tab-PET: Graph-Based Positional Encodings for Tabular Transformers

  Yunze Leng, Rohan Ghosh, Mehul Motani · 18 novembre 2025

  Supervised learning with tabular data presents unique challenges, including low data sizes, the absence of structural cues, and heterogeneous features spanning both categorical and continuous domains. Unlike vision and language tasks, where models can exploit inductive biases in the data, tabular da…

• Graph Out-of-Distribution Detection via Test-Time Calibration with Dual Dynamic Dictionaries

  Yue Hou, Ruomei Liu, Yingke Su, Junran Wu, Ke Xu · 18 novembre 2025

  A key challenge in graph out-of-distribution (OOD) detection lies in the absence of ground-truth OOD samples during training. Existing methods are typically optimized to capture features within the in-distribution (ID) data and calculate OOD scores, which often limits pre-trained models from represe…

• FuseSampleAgg: Fused Neighbor Sampling and Aggregation for Mini-batch GNNs

  Aleksandar Stankovi\'c · 18 novembre 2025

  We present FuseSampleAgg, a CUDA operator that fuses neighbor sampling and mean aggregation into a single pass for one and two hop GraphSAGE. By eliminating block materialization and extra kernel launches, FuseSampleAgg reduces memory traffic and overhead while preserving GraphSAGE mean semantics vi…

• Learning to Refine: An Agentic RL Approach for Iterative SPARQL Query Construction

  Floris Vossebeld, Shenghui Wang · 18 novembre 2025

  Generating complex, logically-sound SPARQL queries for multi-hop questions remains a critical bottleneck for Knowledge Graph Question Answering, as the brittle nature of one-shot generation by Large Language Models (LLMs) hinders reliable interaction with structured data. Current methods lack the ad…

• Fairness-Aware Graph Representation Learning with Limited Demographic Information

  Zichong Wang, Zhipeng Yin, Liping Yang, Jun Zhuang, Rui Yu, Qingzhao Kong, Wenbin Zhang · 18 novembre 2025

  Ensuring fairness in Graph Neural Networks is fundamental to promoting trustworthy and socially responsible machine learning systems. In response, numerous fair graph learning methods have been proposed in recent years. However, most of them assume full access to demographic information, a requireme…

• GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs

  Jiaji Ma, Puja Trivedi, Danai Koutra · 18 novembre 2025

  Text-attributed graphs (TAGs), which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models (LLMs) with Graph Neural Networks (GNNs) to jointly model semantics and structure, resulting in more general and expressive models th…

• InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions

  TC Singh, Sougata Mukherjea · 18 novembre 2025

  Graph Neural Networks (GNNs) excel in graph-based learning tasks, but their complex, non-linear operations often render them as opaque "black boxes". This opacity hinders user trust, complicates debugging, bias detection, and adoption in critical domains requiring explainability. This paper introduc…

• Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learning

  Zhuomin Chen, Jingchao Ni, Hojat Allah Salehi, Xu Zheng, Esteban Schafir, Farhad Shirani, Dongsheng Luo · 18 novembre 2025

  Self-supervised graph representation learning (GRL) typically generates paired graph augmentations from each graph to infer similar representations for augmentations of the same graph, but distinguishable representations for different graphs. While effective augmentation requires both semantics-pres…