Advanced Graph Neural Networks

Derniers papiers

• Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts

  Xinyu Zhao, Qingyun Sun, Jiayi Luo, Xingcheng Fu, Jianxin Li · 9 février 2026

  Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to enable generalization to unseen graph datasets. However, existing zero-shot GAD methods largely ignore intrinsic geometric differences across diverse anomaly pa…

• Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems

  Qifan Zhang, Jianhao Ruan, Aochuan Chen, Kang Zeng, Nuo Chen, Jing Tang, Jia Li · 9 février 2026

  Large Reasoning Models (LRMs) have advanced rapidly; however, existing benchmarks in mathematics, code, and common-sense reasoning remain limited. They lack long-context evaluation, offer insufficient challenge, and provide answers that are difficult to verify programmatically. We introduce GrAlgoBe…

• Which Graph Shift Operator? A Spectral Answer to an Empirical Question

  Yassine Abbahaddou · 9 février 2026

  Graph Neural Networks (GNNs) have established themselves as the leading models for learning on graph-structured data, generally categorized into spatial and spectral approaches. Central to these architectures is the Graph Shift Operator (GSO), a matrix representation of the graph structure used to f…

• Pruning at Initialisation through the lens of Graphon Limit: Convergence, Expressivity, and Generalisation

  Hoang Pham, The-Anh Ta, Long Tran-Thanh · 9 février 2026

  Pruning at Initialisation methods discover sparse, trainable subnetworks before training, but their theoretical mechanisms remain elusive. Existing analyses are often limited to finite-width statistics, lacking a rigorous characterisation of the global sparsity patterns that emerge as networks grow …

• ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks

  Yu Zhang, Sean Bin Yang, Arijit Khan, Cuneyt Gurcan Akcora · 9 février 2026

  Counterfactual explanations offer an intuitive way to interpret graph neural networks (GNNs) by identifying minimal changes that alter a model's prediction, thereby answering "what must differ for a different outcome?". In this work, we propose a novel framework, ATEX-CF that unifies adversarial att…

• Multi-Way Representation Alignment

  Akshit Achara, Tatiana Gaintseva, Mateo Mahaut, Pritish Chakraborty, Viktor Stenby Johansson, Melih Barsbey, Emanuele Rodol\`a, Donato Crisostomi · 9 février 2026

  The Platonic Representation Hypothesis suggests that independently trained neural networks converge to increasingly similar latent spaces. However, current strategies for mapping these representations are inherently pairwise, scaling quadratically with the number of models and failing to yield a con…

• UniRel: Relation-Centric Knowledge Graph Question Answering with RL-Tuned LLM Reasoning

  Yinxu Tang, Chengsong Huang, Jiaxin Huang, William Yeoh · 9 février 2026

  Knowledge Graph Question Answering (KGQA) has largely focused on entity-centric queries that return a single answer entity. However, many real-world questions are inherently relational, aiming to understand how entities are associated rather than which entity satisfies a query. In this work, we intr…

• Implicit Unitarity Bias in Tensor Factorization: A Theoretical Framework for Symmetry Group Discovery

  Dongsung Huh, Halyun Jeong · 9 février 2026

  While modern neural architectures typically generalize via smooth interpolation, it lacks the inductive biases required to uncover algebraic structures essential for systematic generalization. We present the first theoretical analysis of HyperCube, a differentiable tensor factorization architecture …

• Autoregressive Models for Knowledge Graph Generation

  Thiviyan Thanapalasingam, Antonis Vozikis, Peter Bloem, Paul Groth · 9 février 2026

  Knowledge Graph (KG) generation requires models to learn complex semantic dependencies between triples while maintaining domain validity constraints. Unlike link prediction, which scores triples independently, generative models must capture interdependencies across entire subgraphs to produce semant…

• Weisfeiler and Lehman Go Categorical

  Seongjin Choi, Gahee Kim, Se-Young Yun · 9 février 2026

  While lifting map has significantly enhanced the expressivity of graph neural networks, extending this paradigm to hypergraphs remains fragmented. To address this, we introduce the categorical Weisfeiler-Lehman framework, which formalizes lifting as a functorial mapping from an arbitrary data catego…

• MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks

  Long D. Nguyen, Binh P. Nguyen · 6 février 2026

  Pre-trained graph neural networks (GNNs) transfer well, but adapting them to downstream tasks remains challenging due to mismatches between pre-training objectives and task requirements. Graph prompt tuning offers a parameter-efficient alternative to fine-tuning, yet most methods only modify inputs …

• EdgeMask-DG*: Learning Domain-Invariant Graph Structures via Adversarial Edge Masking

  Rishabh Bhattacharya, Naresh Manwani · 6 février 2026

  Structural shifts pose a significant challenge for graph neural networks, as graph topology acts as a covariate that can vary across domains. Existing domain generalization methods rely on fixed structural augmentations or training on globally perturbed graphs, mechanisms that do not pinpoint which …

• Learning Compact Boolean Networks

  Shengpu Wang, Yuhao Mao, Yani Zhang, Martin Vechev · 6 février 2026

  Floating-point neural networks dominate modern machine learning but incur substantial inference cost, motivating interest in Boolean networks for resource-constrained settings. However, learning compact and accurate Boolean networks is challenging due to their combinatorial nature. In this work, we …

• Aspect-Aware MOOC Recommendation in a Heterogeneous Network

  Seongyeub Chu, Jongwoo Kim, Mun Yong Yi · 6 février 2026

  MOOC recommendation systems have received increasing attention to help learners navigate and select preferred learning content. Traditional methods such as collaborative filtering and content-based filtering suffer from data sparsity and over-specialization. To alleviate these limitations, graph-bas…

• Bayesian Neighborhood Adaptation for Graph Neural Networks

  Paribesh Regmi, Rui Li, Kishan K C · 6 février 2026

  The neighborhood scope (i.e., number of hops) where graph neural networks (GNNs) aggregate information to characterize a node's statistical property is critical to GNNs' performance. Two-stage approaches, training and validating GNNs for every pre-specified neighborhood scope to search for the best …

• Interpreting Manifolds and Graph Neural Embeddings from Internet of Things Traffic Flows

  Enrique Feito-Casares, Francisco M. Melgarejo-Meseguer, Elena Casiraghi, Giorgio Valentini, Jos\'e-Luis Rojo-\'Alvarez · 6 février 2026

  The rapid expansion of Internet of Things (IoT) ecosystems has led to increasingly complex and heterogeneous network topologies. Traditional network monitoring and visualization tools rely on aggregated metrics or static representations, which fail to capture the evolving relationships and structura…

• HugRAG: Hierarchical Causal Knowledge Graph Design for RAG

  Nengbo Wang, Tuo Liang, Vikash Singh, Chaoda Song, Van Yang, Yu Yin, Jing Ma, Jagdip Singh, Vipin Chaudhary · 6 février 2026

  Retrieval augmented generation (RAG) has enhanced large language models by enabling access to external knowledge, with graph-based RAG emerging as a powerful paradigm for structured retrieval and reasoning. However, existing graph-based methods often over-rely on surface-level node matching and lack…

• Improving Set Function Approximation with Quasi-Arithmetic Neural Networks

  Tomas Tokar, Scott Sanner · 6 février 2026

  Sets represent a fundamental abstraction across many types of data. To handle the unordered nature of set-structured data, models such as DeepSets and PointNet rely on fixed, non-learnable pooling operations (e.g., sum or max) -- a design choice that can hinder the transferability of learned embeddi…

• From Link Prediction to Forecasting: Addressing Challenges in Batch-based Temporal Graph Learning

  Moritz Lampert, Christopher Bl\"ocker, Ingo Scholtes · 6 février 2026

  Dynamic link prediction is an important problem considered in many recent works that propose approaches for learning temporal edge patterns. To assess their efficacy, models are evaluated on continuous-time and discrete-time temporal graph datasets, typically using a traditional batch-oriented evalu…

• Relational Graph Transformer

  Vijay Prakash Dwivedi, Sri Jaladi, Yangyi Shen, Federico L\'opez, Charilaos I. Kanatsoulis, Rishi Puri, Matthias Fey, Jure Leskovec · 6 février 2026

  Relational Deep Learning (RDL) is a promising approach for building state-of-the-art predictive models on multi-table relational data by representing it as a heterogeneous temporal graph. However, commonly used Graph Neural Network models suffer from fundamental limitations in capturing complex stru…

• Comparing Euclidean and Hyperbolic K-Means for Generalized Category Discovery

  Mohamad Dalal, Thomas B. Moeslund, Joakim Bruslund Haurum · 6 février 2026

  Hyperbolic representation learning has been widely used to extract implicit hierarchies within data, and recently it has found its way to the open-world classification task of Generalized Category Discovery (GCD). However, prior hyperbolic GCD methods only use hyperbolic geometry for representation …

• Breaking Symmetry Bottlenecks in GNN Readouts

  Mouad Talhi, Arne Wolf, Anthea Monod · 6 février 2026

  Graph neural networks (GNNs) are widely used for learning on structured data, yet their ability to distinguish non-isomorphic graphs is fundamentally limited. These limitations are usually attributed to message passing; in this work we show that an independent bottleneck arises at the readout stage.…

• A logical re-conception of neural networks: Hamiltonian bitwise part-whole architecture

  E Bowen, R Granger, A Rodriguez · 6 février 2026

  We introduce a simple initial working system in which relations (such as part-whole) are directly represented via an architecture with operating and learning rules fundamentally distinct from standard artificial neural network methods. Arbitrary data are straightforwardly encoded as graphs whose edg…

• TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learning

  Zihao Jiang, Miao Peng, Zhenyan Shan, Wenjie Xu, Ben Liu, Gong Chen, Ziqi Gao, Min Peng · 6 février 2026

  Temporal knowledge graph question answering (TKGQA) aims to answer time-sensitive questions by leveraging temporal knowledge bases. While Large Language Models (LLMs) demonstrate significant potential in TKGQA, current prompting strategies constrain their efficacy in two primary ways. First, they ar…

• Feedback Control for Multi-Objective Graph Self-Supervision

  Karish Grover, Theodore Vasiloudis, Han Xie, Sixing Lu, Xiang Song, Christos Faloutsos · 6 février 2026

  Can multi-task self-supervised learning on graphs be coordinated without the usual tug-of-war between objectives? Graph self-supervised learning (SSL) offers a growing toolbox of pretext objectives: mutual information, reconstruction, contrastive learning; yet combining them reliably remains a chall…