Advanced Graph Neural Networks

Derniers papiers

• Online Continual Graph Learning

  Giovanni Donghi, Luca Pasa, Daniele Zambon, Cesare Alippi, Nicol\`o Navarin · 19 décembre 2025

  Continual Learning (CL) aims to incrementally acquire new knowledge while mitigating catastrophic forgetting. Within this setting, Online Continual Learning (OCL) focuses on updating models promptly and incrementally from single or small batches of observations from a data stream. Extending OCL to g…

• Microsoft Academic Graph Information Retrieval for Research Recommendation and Assistance

  Jacob Reiss, Shikshya Shiwakoti, Samuel Goldsmith, Ujjwal Pandit · 19 décembre 2025

  In today's information-driven world, access to scientific publications has become increasingly easy. At the same time, filtering through the massive volume of available research has become more challenging than ever. Graph Neural Networks (GNNs) and graph attention mechanisms have shown strong effec…

• Darth Vecdor: An Open-Source System for Generating Knowledge Graphs Through Large Language Model Queries

  Jonathan A. Handler · 19 décembre 2025

  Many large language models (LLMs) are trained on a massive body of knowledge present on the Internet. Darth Vecdor (DV) was designed to extract this knowledge into a structured, terminology-mapped, SQL database ("knowledge base" or "knowledge graph"). Knowledge graphs may be useful in many domains, …

• How Do Graph Signals Affect Recommendation: Unveiling the Mystery of Low and High-Frequency Graph Signals

  Feng Liu, Hao Cang, Huanhuan Yuan, Jiaqing Fan, Yongjing Hao, Fuzhen Zhuang, Guanfeng Liu, Pengpeng Zhao · 19 décembre 2025

  Spectral graph neural networks (GNNs) are highly effective in modeling graph signals, with their success in recommendation often attributed to low-pass filtering. However, recent studies highlight the importance of high-frequency signals. The role of low-frequency and high-frequency graph signals in…

• Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models

  Xueqi Ma, Xingjun Ma, Sarah Monazam Erfani, Danilo Mandic, James Bailey · 19 décembre 2025

  Developing open-set classification methods capable of classifying in-distribution (ID) data while detecting out-of-distribution (OOD) samples is essential for deploying graph neural networks (GNNs) in open-world scenarios. Existing methods typically treat all OOD samples as a single class, despite r…

• Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems

  Jovan Pavlovi\'c, Mikl\'os Kr\'esz, L\'aszl\'o Hajdu · 19 décembre 2025

  Despite initial successes and a variety of architectures, retrieval-augmented generation (RAG) systems still struggle to reliably retrieve and connect the multi-step evidence required for complicated reasoning tasks. Most of the standard RAG frameworks regard all retrieved information as equally rel…

• Sharpness-aware Federated Graph Learning

  Ruiyu Li, Peige Zhao, Guangxia Li, Pengcheng Wu, Xingyu Gao, Zhiqiang Xu · 19 décembre 2025

  One of many impediments to applying graph neural networks (GNNs) to large-scale real-world graph data is the challenge of centralized training, which requires aggregating data from different organizations, raising privacy concerns. Federated graph learning (FGL) addresses this by enabling collaborat…

• IaC Generation with LLMs: An Error Taxonomy and A Study on Configuration Knowledge Injection

  Roman Nekrasov, Stefano Fossati, Indika Kumara, Damian Andrew Tamburri, Willem-Jan van den Heuvel · 18 décembre 2025

  Large Language Models (LLMs) currently exhibit low success rates in generating correct and intent-aligned Infrastructure as Code (IaC). This research investigated methods to improve LLM-based IaC generation, specifically for Terraform, by systematically injecting structured configuration knowledge. …

• RFKG-CoT: Relation-Driven Adaptive Hop-count Selection and Few-Shot Path Guidance for Knowledge-Aware QA

  Chao Zhang, Minghan Li, Tianrui Lv, Guodong Zhou · 18 décembre 2025

  Large language models (LLMs) often generate hallucinations in knowledge-intensive QA due to parametric knowledge limitations. While existing methods like KG-CoT improve reliability by integrating knowledge graph (KG) paths, they suffer from rigid hop-count selection (solely question-driven) and unde…

• Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption

  Sunwoo Kim, Soo Yong Lee, Kyungho Kim, Hyunjin Hwang, Jaemin Yoo, Kijung Shin · 18 décembre 2025

  Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph topology. However, excessive reliance on…

• Exact Verification of Graph Neural Networks with Incremental Constraint Solving

  Minghao Liu, Chia-Hsuan Lu, Marta Kwiatkowska · 18 décembre 2025

  Graph neural networks (GNNs) are increasingly employed in high-stakes applications, such as fraud detection or healthcare, but are susceptible to adversarial attacks. A number of techniques have been proposed to provide adversarial robustness guarantees, but support for commonly used aggregation fun…

• SEA: Spectral Edge Attack

  Yongyu Wang · 18 décembre 2025

  Graph based machine learning algorithms occupy an important position in today AI landscape. The ability of graph topology to represent complex data structures is both the key strength of graph algorithms and a source of their vulnerability. In other words, attacking or perturbing a graph can severel…

• ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs

  Turja Kundu, Sanjukta Bhowmick · 18 décembre 2025

  We present ATLAS (Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs), a novel graph learning algorithm that addresses two important challenges in graph neural networks (GNNs). First, the accuracy of GNNs degrades when the graph is heterophilic. Second, iterative featur…

• GR-Agent: Adaptive Graph Reasoning Agent under Incomplete Knowledge

  Dongzhuoran Zhou, Yuqicheng Zhu, Xiaxia Wang, Hongkuan Zhou, Jiaoyan Chen, Steffen Staab, Yuan He, Evgeny Kharlamov · 18 décembre 2025

  Large language models (LLMs) achieve strong results on knowledge graph question answering (KGQA), but most benchmarks assume complete knowledge graphs (KGs) where direct supporting triples exist. This reduces evaluation to shallow retrieval and overlooks the reality of incomplete KGs, where many fac…

• How Smoothing is N-simplicial Attention?

  Alexandre Dussolle, Pietro Li\`o · 18 décembre 2025

  Going from pure Multilayer Perceptron (MLP) to a learnable graph message-passing mechanism at each layer has been foundational to state-of-the-art results, despite the computational trade-off (e.g. GATs or Transformers). To go a step further, in this work, we introduce N-simplicial attention, going …

• HeSRN: Representation Learning On Heterogeneous Graphs via Slot-Aware Retentive Network

  Yifan Lu, Ziyun Zou, Belal Alsinglawi, Islam Al-Qudah, Izzat Alsmadi, Feilong Tang, Pengfei Jiao, Shoaib Jameel, Imran Razzak · 17 décembre 2025

  Graph Transformers have recently achieved remarkable progress in graph representation learning by capturing long-range dependencies through self-attention. However, their quadratic computational complexity and inability to effectively model heterogeneous semantics severely limit their scalability an…

• Beyond MMD: Evaluating Graph Generative Models with Geometric Deep Learning

  Salvatore Romano, Marco Grassia, Giuseppe Mangioni · 17 décembre 2025

  Graph generation is a crucial task in many fields, including network science and bioinformatics, as it enables the creation of synthetic graphs that mimic the properties of real-world networks for various applications. Graph Generative Models (GGMs) have emerged as a promising solution to this probl…

• GALAX: Graph-Augmented Language Model for Explainable Reinforcement-Guided Subgraph Reasoning in Precision Medicine

  Heming Zhang, Di Huang, Wenyu Li, Michael Province, Yixin Chen, Philip Payne, Fuhai Li · 17 décembre 2025

  In precision medicine, quantitative multi-omic features, topological context, and textual biological knowledge play vital roles in identifying disease-critical signaling pathways and targets. Existing pipelines capture only part of these-numerical omics ignore topological context, text-centric LLMs …

• Enhancing Semi-Supervised Multi-View Graph Convolutional Networks via Supervised Contrastive Learning and Self-Training

  Huaiyuan Xiao, Fadi Dornaika, Jingjun Bi · 17 décembre 2025

  The advent of graph convolutional network (GCN)-based multi-view learning provides a powerful framework for integrating structural information from heterogeneous views, enabling effective modeling of complex multi-view data. However, existing methods often fail to fully exploit the complementary inf…

• A Complete Guide to Spherical Equivariant Graph Transformers

  Sophia Tang · 17 décembre 2025

  Spherical equivariant graph neural networks (EGNNs) provide a principled framework for learning on three-dimensional molecular and biomolecular systems, where predictions must respect the rotational symmetries inherent in physics. These models extend traditional message-passing GNNs and Transformers…

• Implicit Bias and Invariance: How Hopfield Networks Efficiently Learn Graph Orbits

  Michael Murray, Tenzin Chan, Kedar Karhadker, Christopher J. Hillar · 17 décembre 2025

  Many learning problems involve symmetries, and while invariance can be built into neural architectures, it can also emerge implicitly when training on group-structured data. We study this phenomenon in classical Hopfield networks and show they can infer the full isomorphism class of a graph from a s…

• Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual Accuracy

  Steve Nwaiwu, Nipat Jongsawat, Anucha Tungkasthan · 17 décembre 2025

  Causal reasoning in Large Language Models spanning association, intervention, and counterfactual inference is essential for reliable decision making in high stakes settings. As deployment shifts toward edge and resource constrained environments, quantized models such as INT8 and NF4 are becoming sta…

• ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning

  Chaohao Yuan, Zhenjie Song, Ercan Engin Kuruoglu, Kangfei Zhao, Yang Liu, Deli Zhao, Hong Cheng, Yu Rong · 17 décembre 2025

  Graph Transformers (GTs) have emerged as a promising graph learning tool, leveraging their all-pair connected property to effectively capture global information. To address the over-smoothing problem in deep GNNs, global attention was initially introduced, eliminating the necessity for using deep GN…

• TinyGraphEstimator: Adapting Lightweight Language Models for Graph Structure Inference

  Michal Podstawski · 16 décembre 2025

  Graphs provide a universal framework for representing complex relational systems, and inferring their structural properties is a core challenge in graph analysis and reasoning. While large language models have recently demonstrated emerging abilities to perform symbolic and numerical reasoning, the …

• SA$^{2}$GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation

  Junhua Shi, Qingyun Sun, Haonan Yuan, Xingcheng Fu · 16 décembre 2025

  We present Graph Foundation Models (GFMs) which have made significant progress in various tasks, but their robustness against domain noise, structural perturbations, and adversarial attacks remains underexplored. A key limitation is the insufficient modeling of hierarchical structural semantics, whi…