Advanced Graph Neural Networks

Derniers papiers

• The Correspondence Between Bounded Graph Neural Networks and Fragments of First-Order Logic

  Bernardo Cuenca Grau, Eva Feng, Przemys{\l}aw Andrzej Wa{\l}\k{e}ga · 20 février 2026

  Graph Neural Networks (GNNs) address two key challenges in applying deep learning to graph-structured data: they handle varying size input graphs and ensure invariance under graph isomorphism. While GNNs have demonstrated broad applicability, understanding their expressive power remains an important…

• AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation

  Rong Fu, Muge Qi, Chunlei Meng, Shuo Yin, Kun Liu, Zhaolu Kang, Simon Fong · 20 février 2026

  Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies. To address these systemic vulnerabilities, we present AdvSynGNN, a comprehensive architecture designed for resilient node-level representation learning.…

• Generating Directed Graphs with Dual Attention and Asymmetric Encoding

  Alba Carballo-Castro, Manuel Madeira, Yiming Qin, Dorina Thanou, Pascal Frossard · 20 février 2026

  Directed graphs naturally model systems with asymmetric, ordered relationships, essential to applications in biology, transportation, social networks, and visual understanding. Generating such graphs enables tasks such as simulation, data augmentation and novel instance discovery; however, directed …

• Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning

  Adrian Arnaiz-Rodriguez, Federico Errica · 20 février 2026

  After a renaissance phase in which researchers revisited the message-passing paradigm through the lens of deep learning, the graph machine learning community shifted its attention towards a deeper and practical understanding of message-passing's benefits and limitations. In this paper, we notice how…

• Enhancing Large Language Models (LLMs) for Telecom using Dynamic Knowledge Graphs and Explainable Retrieval-Augmented Generation

  Dun Yuan (Charlie), Hao Zhou (Charlie), Xue Liu (Charlie), Hao Chen (Charlie), Yan Xin (Charlie), Jianzhong (Charlie), Zhang · 20 février 2026

  Large language models (LLMs) have shown strong potential across a variety of tasks, but their application in the telecom field remains challenging due to domain complexity, evolving standards, and specialized terminology. Therefore, general-domain LLMs may struggle to provide accurate and reliable o…

• From Subtle to Significant: Prompt-Driven Self-Improving Optimization in Test-Time Graph OOD Detection

  Luzhi Wang, Xuanshuo Fu, He Zhang, Chuang Liu, Xiaobao Wang, Hongbo Liu · 20 février 2026

  Graph Out-of-Distribution (OOD) detection aims to identify whether a test graph deviates from the distribution of graphs observed during training, which is critical for ensuring the reliability of Graph Neural Networks (GNNs) when deployed in open-world scenarios. Recent advances in graph OOD detect…

• RLGT: A reinforcement learning framework for extremal graph theory

  Ivan Damnjanovi\'c, Uro\v{s} Milivojevi\'c, Irena {\DJ}or{\dj}evi\'c, Dragan Stevanovi\'c · 20 février 2026

  Reinforcement learning (RL) is a subfield of machine learning that focuses on developing models that can autonomously learn optimal decision-making strategies over time. In a recent pioneering paper, Wagner demonstrated how the Deep Cross-Entropy RL method can be applied to tackle various problems f…

• Semi-Supervised Learning on Graphs using Graph Neural Networks

  Juntong Chen, Claire Donnat, Olga Klopp, Johannes Schmidt-Hieber · 20 février 2026

  Graph neural networks (GNNs) work remarkably well in semi-supervised node regression, yet a rigorous theory explaining when and why they succeed remains lacking. To address this gap, we study an aggregate-and-readout model that encompasses several common message passing architectures: node features …

• Instructor-Aligned Knowledge Graphs for Personalized Learning

  Abdulrahman AlRabah, Priyanka Kargupta, Jiawei Han, Abdussalam Alawini · 20 février 2026

  Mastering educational concepts requires understanding both their prerequisites (e.g., recursion before merge sort) and sub-concepts (e.g., merge sort as part of sorting algorithms). Capturing these dependencies is critical for identifying students' knowledge gaps and enabling targeted intervention f…

• A Locality Radius Framework for Understanding Relational Inductive Bias in Database Learning

  Aadi Joshi, Kavya Bhand · 20 février 2026

  Foreign key discovery and related schema-level prediction tasks are often modeled using graph neural networks (GNNs), implicitly assuming that relational inductive bias improves performance. However, it remains unclear when multi-hop structural reasoning is actually necessary. In this work, we intro…

• Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learning

  Chuqin Geng, Li Zhang, Haolin Ye, Ziyu Zhao, Yuhe Jiang, Tara Saba, Xinyu Wang, Xujie Si · 20 février 2026

  Graph Neural Networks (GNNs) have become essential in high-stakes domains such as drug discovery, yet their black-box nature remains a significant barrier to trustworthiness. While self-explainable GNNs attempt to bridge this gap, they often rely on standard message-passing backbones that inherit fu…

• Predicting The Cop Number Using Machine Learning

  Meagan Mann, Christian Muise, Erin Meger · 19 février 2026

  Cops and Robbers is a pursuit evasion game played on a graph, first introduced independently by Quilliot \cite{quilliot1978jeux} and Nowakowski and Winkler \cite{NOWAKOWSKI1983235} over four decades ago. A main interest in recent the literature is identifying the cop number of graph families. The co…

• A Graph Meta-Network for Learning on Kolmogorov-Arnold Networks

  Guy Bar-Shalom, Ami Tavory, Itay Evron, Maya Bechler-Speicher, Ido Guy, Haggai Maron · 19 février 2026

  Weight-space models learn directly from the parameters of neural networks, enabling tasks such as predicting their accuracy on new datasets. Naive methods -- like applying MLPs to flattened parameters -- perform poorly, making the design of better weight-space architectures a central challenge. Whil…

• Transformers Provably Learn Algorithmic Solutions for Graph Connectivity, But Only with the Right Data

  Qilin Ye, Deqing Fu, Robin Jia, Vatsal Sharan · 19 février 2026

  Transformers often fail to learn generalizable algorithms, instead relying on brittle heuristics. Using graph connectivity as a testbed, we explain this phenomenon both theoretically and empirically. We consider a simplified Transformer architecture, the Disentangled Transformer, and prove that an $…

• Linked Data Classification using Neurochaos Learning

  Pooja Honna, Ayush Patravali, Nithin Nagaraj, Nanjangud C. Narendra · 19 février 2026

  Neurochaos Learning (NL) has shown promise in recent times over traditional deep learning due to its two key features: ability to learn from small sized training samples, and low compute requirements. In prior work, NL has been implemented and extensively tested on separable and time series data, an…

• Investigating GNN Convergence on Large Randomly Generated Graphs with Realistic Node Feature Correlations

  Mohammed Zain Ali Ahmed · 19 février 2026

  There are a number of existing studies analysing the convergence behaviour of graph neural networks on large random graphs. Unfortunately, the majority of these studies do not model correlations between node features, which would naturally exist in a variety of real-life networks. Consequently, the …

• Expressive Power of Graph Transformers via Logic

  Veeti Ahvonen, Maurice Funk, Damian Heiman, Antti Kuusisto, Carsten Lutz · 19 février 2026

  Transformers are the basis of modern large language models, but relatively little is known about their precise expressive power on graphs. We study the expressive power of graph transformers (GTs) by Dwivedi and Bresson (2020) and GPS-networks by Ramp\'asek et al. (2022), both under soft-attention a…

• Including Node Textual Metadata in Laplacian-constrained Gaussian Graphical Models

  Jianhua Wang, Killian Cressant, Pedro Braconnot Velloso, Arnaud Breloy · 19 février 2026

  This paper addresses graph learning in Gaussian Graphical Models (GGMs). In this context, data matrices often come with auxiliary metadata (e.g., textual descriptions associated with each node) that is usually ignored in traditional graph estimation processes. To fill this gap, we propose a graph le…

• NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering

  Rong Fu, Yang Li, Zeyu Zhang, Jiekai Wu, Yaohua Liu, Shuaishuai Cao, Yangchen Zeng, Yuhang Zhang, Xiaojing Du, Chuang Zhao, Kangning Cui, Simon Fong · 18 février 2026

  Large pretrained language models and neural reasoning systems have advanced many natural language tasks, yet they remain challenged by knowledge-intensive queries that require precise, structured multi-hop inference. Knowledge graphs provide a compact symbolic substrate for factual grounding, but in…

• On the Geometric Coherence of Global Aggregation in Federated GNN

  Chethana Prasad Kabgere, Shylaja SS · 18 février 2026

  Federated Learning (FL) enables distributed training across multiple clients without centralized data sharing, while Graph Neural Networks (GNNs) model relational data through message passing. In federated GNN settings, client graphs often exhibit heterogeneous structural and propagation characteris…

• Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors

  Erkan Turan, Gaspard Abel, Maysam Behmanesh, Emery Pierson, Maks Ovsjanikov · 18 février 2026

  Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from oversmoothing, where node features converge to a homogeneous, non-informative state. We re-frame this problem of representational collapse from a \emph{bifur…

• Random Wavelet Features for Graph Kernel Machines

  Valentin de Bassompierre, Jean-Charles Delvenne, Laurent Jacques · 18 février 2026

  Node embeddings map graph vertices into low-dimensional Euclidean spaces while preserving structural information. They are central to tasks such as node classification, link prediction, and signal reconstruction. A key goal is to design node embeddings whose dot products capture meaningful notions o…

• Embedding Retrofitting: Data Engineering for better RAG

  Anantha Sharma · 18 février 2026

  Embedding retrofitting adjusts pre-trained word vectors using knowledge graph constraints to improve domain-specific retrieval. However, the effectiveness of retrofitting depends critically on knowledge graph quality, which in turn depends on text preprocessing. This paper presents a data engineerin…

• Size Transferability of Graph Transformers with Convolutional Positional Encodings

  Javier Porras-Valenzuela, Zhiyang Wang, Alejandro Ribeiro · 18 février 2026

  Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. A key design choice in GTs is the use of Graph Neural Network (GNN)-based positional encodings to incorporate structural informati…

• Flock: A Knowledge Graph Foundation Model via Learning on Random Walks

  Jinwoo Kim, Xingyue Huang, Krzysztof Olejniczak, Kyungbin Min, Michael Bronstein, Seunghoon Hong, \.Ismail \.Ilkan Ceylan · 18 février 2026

  We study the problem of zero-shot link prediction on knowledge graphs (KGs), which requires models to generalize to novel entities and novel relations. Knowledge graph foundation models (KGFMs) address this task by enforcing equivariance over both nodes and relations, which enables them to learn str…