In graph-level learning, graph neural networks are typically applied with a fixed computational template: the same depth, local message-passing operator, and global attention mechanism are used for every input graph. However, different graphs within the same dataset can vary substantially in prediction difficulty and may require different mixtures of local and non-local computation. We study this phenomenon as graph-level heterogeneity in both classification and regression tasks. To address it, we propose SiGMA (Sigmoid Gated Message-Passing and Attention), a gated hybrid graph neural network architecture that combines message-passing and attention heads within each layer. Inspired by the growing use of gated attention and gated computation in large language models and vision transformers, each head in SiGMA is modulated by a learned node-wise sigmoid gate, allowing the model to adaptively regulate which local or global mechanisms are active for different nodes, layers, and input graphs. The resulting architecture can emulate expressive message-passing backbones, admits near-identity computation paths that are not forced to over-smooth, and enables direct non-local communication beyond message-passing neighborhoods to mitigate over-squashing. Empirically, SiGMA achieves strong performance across graph-level benchmarks, consistently matching or improving over competitive graph transformer and hybrid baselines. Our results suggest that adapting computation to graph-level heterogeneity is a promising direction for building more flexible and effective graph learning architectures.
HINormer: Representation Learning On Heterogeneous Information Networks with Graph Transformer
Zhejiang University(浙江大学);National University of Singapore(新加坡国立大学);Salesforce Research Asia(Salesforce亚洲研究院);Alibaba-Zhejiang University Joint Institute of Frontier Technologies(阿里巴巴-浙江大学前沿技术联合研究院)
Graph Convolutional Network With Pattern-Spatial Interactive and Regional Awareness for Traffic Forecasting
College of Mechanical and Electrical Engineering, Shihezi University(石河子大学机械与电子工程学院);School of Mathematics and Computational Science, Xiangtan University(湘潭大学数学与计算机科学学院);College of Sciences, Shihezi University(石河子大学科学学院)
Equivariant Machine Learning Interatomic Potentials with Global Charge Redistribution
Department of Mechanical Engineering, Texas Tech University, Lubbock, Texas 79409, USA(德克萨斯理工大学机械工程系);Samsung Advanced Institute of Technology, Samsung Electronics, Suwon 16678, Republic of Korea(三星电子首尔先进技术研究所)
Decoupled Structure-Feature Alignment via Alternating Optimization for Graph Learning
College of Artificial Intelligence, Shaoxing Institute of Technology(绍兴文理学院人工智能学院);School of Mathematics and Computational Science, Xiangtan University(湘潭大学数学与计算科学学院)
Dynamic Sheaf Diffusion Networks with Adaptive Local Structure for Heterogeneous Spatio-Temporal Graph Learning
Peter L. Reichertz Institute for Medical Informatics(汉诺威医学院彼得·L·里赫茨医学信息学研究所);Hannover Medical School(汉诺威医学院);Lower Saxony Center for Artificial Intelligence and Causal Methods in Medicine (CAIMed)(下萨克森人工智能与医学因果方法中心(CAIMed))
Toward Practical Entity Alignment Method Design: Insights from New Highly Heterogeneous Knowledge Graph Datasets
CAS Key Laboratory of AI Safety & Security, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所人工智能安全与安全重点实验室);School of Computer Science and Technology, University of Chinese Academy of Science(中国科学院大学计算机科学与技术学院);IDEA Research, International Digital Economy Academy(国际数字经济学院 IDEA 研究院);National University of Defense Technology(国防科技大学)
Message Passing Based Two-Timescale Bayesian Learning for Joint Channel and Memory Hardware Impairments Tracking
Zhejiang University(浙江大学);National Key Laboratory of Millimeter-Wave and Terahertz Remote Sensing(毫米波与太赫兹遥感全国重点实验室);Zhejiang Provincial Key Laboratory of Information Processing, Communication and Networking (IPCAN)(浙江省信息处理、通信与网络重点实验室);Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing(浙江省多模态通信网络与智能信息处理重点实验室)
FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
Wuhan University(武汉大学);National Engineering Research Center for Multimedia Software(国家多媒体软件工程技术研究中心);Institute of Artificial Intelligence(人工智能研究院);School of Computer Science(计算机学院);Taikang Center for Life and Medical Sciences(泰康生命与医学科学中心)
Graph neural networks for residential location choice: connection to classical logit models
Department of Urban and Regional Planning, University of Florida(佛罗里达大学城市与区域规划系);Department of Landscape Architecture and Urban Planning, Texas A&M University(德克萨斯大学农业与机械学院景观建筑与城市规划系);Department of Computer Science, University of California, Santa Barbara(加州大学圣芭芭拉分校计算机科学系)
On LLM-Enhanced Mixed-Type Data Imputation with High-Order Message Passing
The University of New South Wales(新南威尔士大学);Antai College of Economics & Management, Shanghai Jiao Tong University(上海交通大学安泰经济与管理学院);Zhejiang Gongshang University(浙江工商大学);Data61, CSIRO(联邦科学与工业研究组织Data61研究院)
UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment
Department of XXX, University of YYY, Location, Country(XXX系,YYY大学,Location,Country);School of ZZZ, Institute of WWW, Location, Country(ZZZ学院,WWW研究所,Location,Country)
Fed-GAME: Personalized Federated Learning with Graph Attention Mixture-of-Experts For Time-Series Forecasting
School of Automation, Central South University(中南大学自动化学院);Department of Electrical and Computer Engineering, National University of Singapore(新加坡国立大学电气与计算机工程系);Department of Mechanical Engineering, National University of Singapore(新加坡国立大学机械工程系);School of Electrical Engineering and Telecommunications, University of New South Wales(新南威尔士大学电气工程与电信学院);Department of Electrical Engineering, City University of Hong Kong(香港城市大学电子工程系)
FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts
Yunnan University(云南大学);Carnegie Mellon University(卡内基梅隆大学);Griffith University(格里菲斯大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));Beijing Jiaotong University(北京交通大学)