In recent years, there has been a surge in research on dynamic graph representation learning, primarily focusing on modeling the evolution of temporal-spatial patterns in real-world applications. However, within the domain of discrete-time dynamic graphs, the exploration of temporal edges remains underexplored. Existing approaches often rely on additional sequential models to capture dynamics, leading to high computational and memory costs, particularly for large-scale graphs. To address this limitation, we propose the Input {\bf S}napshots {\bf F}usion based {\bf Dy}namic {\bf G}raph Neural Network (SFDyG), which combines Hawkes processes with graph neural networks to capture temporal and structural patterns in dynamic graphs effectively. By fusing multiple snapshots into a single temporal graph, SFDyG decouples computational complexity from the number of snapshots, enabling efficient full-batch and mini-batch training. Experimental evaluations on eight diverse dynamic graph datasets for future link prediction tasks demonstrate that SFDyG consistently outperforms existing methods.
ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion
Ocean University of China（海洋大学）；Harbin Institute of Technology（哈尔滨工业大学）；Shandong University of Science and Technology（山东科技大学）；School of Computer, National University of Defense Technology（国防科技大学计算机学院）
Experimental results on palmvein-based personal recognition by multi-snapshot fusion of textural features
Department of Computer Science, University of Milan（米兰大学计算机科学系）；Department of Electrical and Electronic Engineering, University of Cagliari（卡利亚里大学电气与电子工程系）；University of Milan（米兰大学）；University of Cagliari（卡利亚里大学）
Scalable learning of macroscopic stochastic dynamics
Department of Mathematics, National University of Singapore, Singapore, Singapore（新加坡国立大学数学系）；Institute for Functional Intelligent Materials, National University of Singapore, Singapore, Singapore（新加坡国立大学功能智能材料研究所）；Engineering, National University of Singapore, Singapore, Singapore（新加坡国立大学工程系）
Cross-Modal Binary Attention: An Energy-Efficient Fusion Framework for Audio-Visual Learning
Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School（图林根工业大学和汉诺威医学院医学信息学研究所）；Lower Saxony Center for AI and Causal Methods in Medicine (CAIMed)（下萨克森人工智能与因果医学方法中心）
Mitigating Homophily Disparity in Graph Anomaly Detection: A Scalable and Adaptive Approach
State Key Laboratory for Novel Software Technology（新型软件技术国家重点实验室）；Nanjing University（南京大学）；National Engineering Laboratory for Big Data Analysis and Applications（大数据分析与应用国家工程实验室）；Peking University（北京大学）
MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion
Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学）；Research Institute of Multiple Agents and Embodied Intelligence, Pengcheng Laboratory（多智能体与具身智能研究院，鹏城实验室）
Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator
1 Institute of Science；Technology Austria, Am Campus 1, 3400 Klosterneuburg, Austria 2 Vienna Center for Quantum Science；Technology (VCQ), Atominstitut, TU Wien, Vienna, Austria 3 ICFO – Institut de Ci\`encies Fot\`oniques, The Barcelona Institute of Science；Technology, Av. Carl Friedrich Gauss 3, 08860 Castelldefels (Barcelona), Spain 4 University of Innsbruck, Department for Theoretical Physics, Technikerstr. 21a, A-6020 Innsbruck, Austria
Decentralized Data Fusion and Active Sensing with Mobile Sensors for Modeling and Predicting Spatiotemporal Traffic Phenomena
National University of Singapore（新加坡国立大学）；Singapore-MIT Alliance for Research and Technology（新加坡-麻省理工学院研究与技术联盟）；MIT（麻省理工学院）；Carnegie Mellon University（卡内基梅隆大学）；University of Southern California（南加州大学）
