Advanced Graph Neural Networks

Derniers papiers

• Federated Learning of Nonlinear Temporal Dynamics with Graph Attention-based Cross-Client Interpretability

  Ayse Tursucular, Ayush Mohanty, Nazal Mohamed, Nagi Gebraeel · 17 février 2026

  Networks of modern industrial systems are increasingly monitored by distributed sensors, where each system comprises multiple subsystems generating high dimensional time series data. These subsystems are often interdependent, making it important to understand how temporal patterns at one subsystem r…

• G2CP: A Graph-Grounded Communication Protocol for Verifiable and Efficient Multi-Agent Reasoning

  Karim Ben Khaled, Davy Monticolo · 17 février 2026

  Multi-agent systems powered by Large Language Models face a critical challenge: agents communicate through natural language, leading to semantic drift, hallucination propagation, and inefficient token consumption. We propose G2CP (Graph-Grounded Communication Protocol), a structured agent communicat…

• Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation

  Cai Zhou, Zijie Chen, Zian Li, Jike Wang, Kaiyi Jiang, Pan Li, Rose Yu, Muhan Zhang, Stephen Bates, Tommi Jaakkola · 17 février 2026

  Many generative tasks in chemistry and science involve distributions invariant to group symmetries (e.g., permutation and rotation). A common strategy enforces invariance and equivariance through architectural constraints such as equivariant denoisers and invariant priors. In this paper, we challeng…

• Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization

  Rizhen Hu, Yuan Cao, Boao Kong, Mou Sun, Kun Yuan · 17 février 2026

  Sparse Mixture-of-Experts (MoE) models scale Transformers efficiently but suffer from expert overlap -- redundant representations across experts and routing ambiguity, resulting in severely underutilized model capacity. While architectural solutions like DeepSeekMoE promote specialization, they requ…

• Optimization-Free Graph Embedding via Distributional Kernel for Community Detection

  Shuaibin Song, Kai Ming Ting, Kaifeng Zhang, Tianrun Liang · 17 février 2026

  Neighborhood Aggregation Strategy (NAS) is a widely used approach in graph embedding, underpinning both Graph Neural Networks (GNNs) and Weisfeiler-Lehman (WL) methods. However, NAS-based methods are identified to be prone to over-smoothing-the loss of node distinguishability with increased iteratio…

• Return of the Schema: Building Complete Datasets for Machine Learning and Reasoning on Knowledge Graphs

  Ivan Diliso, Roberto Barile, Claudia d'Amato, Nicola Fanizzi · 17 février 2026

  Datasets for the experimental evaluation of knowledge graph refinement algorithms typically contain only ground facts, retaining very limited schema level knowledge even when such information is available in the source knowledge graphs. This limits the evaluation of methods that rely on rich ontolog…

• BHyGNN+: Unsupervised Representation Learning for Heterophilic Hypergraphs

  Tianyi Ma, Yiyue Qian, Zehong Wang, Zheyuan Zhang, Chuxu Zhang, Yanfang Ye · 17 février 2026

  Hypergraph Neural Networks (HyGNNs) have demonstrated remarkable success in modeling higher-order relationships among entities. However, their performance often degrades on heterophilic hypergraphs, where nodes connected by the same hyperedge tend to have dissimilar semantic representations or belon…

• A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction

  Nafiseh Sadat Sajadi, Behnam Bahrak, Mahdi Jafari Siavoshani · 17 février 2026

  Predicting links in sparse, continuously evolving networks is a central challenge in network science. Conventional heuristic methods and deep learning models, including Graph Neural Networks (GNNs), are typically designed for static graphs and thus struggle to capture temporal dependencies. Snapshot…

• Importance Ranking in Complex Networks via Influence-aware Causal Node Embedding

  Jiahui Gao, Kuang Zhou, Yuchen Zhu, Keyu Wu · 17 février 2026

  Understanding and quantifying node importance is a fundamental problem in network science and engineering, underpinning a wide range of applications such as influence maximization, social recommendation, and network dismantling. Prior research often relies on centrality measures or advanced graph em…

• HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs

  Xingyue Huang, Mikhail Galkin, Michael M. Bronstein, \.Ismail \.Ilkan Ceylan · 17 février 2026

  Inductive link prediction with knowledge hypergraphs is the task of predicting missing hyperedges involving completely novel entities (i.e., nodes unseen during training). Existing methods for inductive link prediction with knowledge hypergraphs assume a fixed relational vocabulary and, as a result,…

• What Do Temporal Graph Learning Models Learn?

  Abigail J. Hayes, Tobias Schumacher, Markus Strohmaier · 16 février 2026

  Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models. However, recent work has raised concerns about the reliability of benchmark results, noting issues with commonly used evalua…

• AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning

  Bowen Ping, Minnan Luo, Zhuohang Dang, Chenxi Wang, Chengyou Jia · 16 février 2026

  Geometry problem solving presents distinctive challenges in artificial intelligence, requiring exceptional multimodal comprehension and rigorous mathematical reasoning capabilities. Existing approaches typically fall into two categories: neural-based and symbolic-based methods, both of which exhibit…

• Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding

  Chundong Liang, Yongqi Huang, Dongxiao He, Peiyuan Li, Yawen Li, Di Jin, Weixiong Zhang · 16 février 2026

  Graph pre-training has achieved remarkable success in recent years, delivering transferable representations for downstream adaptation. However, most existing methods are designed for either homogeneous or heterogeneous graphs, thereby hindering unified graph modeling across diverse graph types. This…

• Rational Neural Networks have Expressivity Advantages

  Maosen Tang, Alex Townsend · 16 février 2026

  We study neural networks with trainable low-degree rational activation functions and show that they are more expressive and parameter-efficient than modern piecewise-linear and smooth activations such as ELU, LeakyReLU, LogSigmoid, PReLU, ReLU, SELU, CELU, Sigmoid, SiLU, Mish, Softplus, Tanh, Softmi…

• SWING: Unlocking Implicit Graph Representations for Graph Random Features

  Alessandro Manenti, Avinava Dubey, Arijit Sehanobish, Cesare Alippi, Krzysztof Choromanski · 16 février 2026

  We propose SWING: Space Walks for Implicit Network Graphs, a new class of algorithms for computations involving Graph Random Features on graphs given by implicit representations (i-graphs), where edge-weights are defined as bi-variate functions of feature vectors in the corresponding nodes. Those cl…

• Intent-Driven Smart Manufacturing Integrating Knowledge Graphs and Large Language Models

  Takoua Jradi, John Violos, Dimitrios Spatharakis, Lydia Mavraidi, Ioannis Dimolitsas, Aris Leivadeas, Symeon Papavassiliou · 16 février 2026

  The increasing complexity of smart manufacturing environments demands interfaces that can translate high-level human intents into machine-executable actions. This paper presents a unified framework that integrates instruction-tuned Large Language Models (LLMs) with ontology-aligned Knowledge Graphs …

• Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting

  Siyuan Li, Yunjia Wu, Yiyong Xiao, Pingyang Huang, Peize Li, Ruitong Liu, Yan Wen, Te Sun, Fangyi Pei · 16 février 2026

  Temporal knowledge graph (TKG) forecasting requires predicting future facts by jointly modeling structural dependencies within each snapshot and temporal evolution across snapshots. However, most existing methods are stateless: they recompute entity representations at each timestamp from a limited q…

• Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction

  Zulun Zhu, Siqiang Luo · 16 février 2026

  Temporal Graph Neural Networks (TGNNs) are pivotal in processing dynamic graphs. However, existing TGNNs primarily target one-time predictions for a given temporal span, whereas many practical applications require continuous predictions, that predictions are issued frequently over time. Directly ada…

• Which Algorithms Can Graph Neural Networks Learn?

  Solveig Wittig, Antonis Vasileiou, Robert R. Nerem, Timo Stoll, Floris Geerts, Yusu Wang, Christopher Morris · 16 février 2026

  In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a line of work often referred to as neural algorithmic reasoning. The goal is to integrate algorithmic reasoning capabilities into larger neural pipelines. Many su…

• HyperMLP: An Integrated Perspective for Sequence Modeling

  Jiecheng Lu, Shihao Yang · 16 février 2026

  Self-attention is often viewed as probabilistic query-key lookup, motivating designs that preserve normalized attention scores and fixed positional semantics. We advocate a simpler and more unified perspective: an autoregressive attention head can be viewed as a dynamic two-layer MLP whose weights a…

• ThinkRouter: Efficient Reasoning via Routing Thinking between Latent and Discrete Spaces

  Xin Xu, Tong Yu, Xiang Chen, Haoliang Wang, Julian McAuley, Saayan Mitra · 13 février 2026

  Recent work explores latent reasoning to improve reasoning efficiency by replacing explicit reasoning trajectories with continuous representations in a latent space, yet its effectiveness varies across settings. Analysis of model confidence dynamics under latent reasoning reveals that thinking traje…

• Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs

  Yinlin Zhu, Di Wu, Xu Wang, Guocong Quan, Miao Hu · 13 février 2026

  Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural information. While effective on in-distribution (ID) data, GNNs often encounter out-of-distribution (OOD) nodes with unseen textual or structural patterns…

• Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems

  Wanxing Wu, He Zhu, Yixia Li, Lei Yang, Jiehui Zhao, Hongru Wang, Jian Yang, Benyou Wang, Bingyi Jing, Guanhua Chen · 13 février 2026

  Large language models (LLMs) have achieved success, but cost and privacy constraints necessitate deploying smaller models locally while offloading complex queries to cloud-based models. Existing router evaluations are unsystematic, overlooking scenario-specific requirements and out-of-distribution r…

• Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design

  Jialiang Wang, Hanmo Liu, Shimin Di, Zhili Wang, Jiachuan Wang, Lei Chen, Xiaofang Zhou · 13 février 2026

  Designing high-performance neural networks for new tasks requires balancing optimization quality with search efficiency. Current methods fail to achieve this balance: neural architectural search is computationally expensive, while model retrieval often yields suboptimal static checkpoints. To resolv…

• Tiny Recursive Reasoning with Mamba-2 Attention Hybrid

  Wenlong Wang, Fergal Reid · 13 février 2026

  Recent work on recursive reasoning models like TRM demonstrates that tiny networks (7M parameters) can achieve strong performance on abstract reasoning tasks through latent recursion -- iterative refinement in hidden representation space without emitting intermediate tokens. This raises a natural qu…