Dynamic Graph Learning

Follow this topic Ask about this topic

Dynamic graph learning studies networks whose connections, attributes, or both evolve, from timestamped interaction events to sequences of graph snapshots. Common approaches include temporal graph neural networks with memory, attention, or state-space models, alongside methods that learn changing graph structure, temporal representations, or causal patterns. They are used for tasks such as link and event prediction, anomaly detection, traffic forecasting, and analysis of brain or transaction networks. A central challenge is balancing responsiveness to new patterns with retention of useful history, while ensuring efficient, interpretable models are evaluated under realistic distribution shifts and negative-sampling protocols.

Latest papers

124 papers12 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting
Apr 8, 2026Yeran Zhang, Pengwei Yang, Guoqing Wang +1Time Series Forecasting Multivariate Time Series Forecasting
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China · Research Center, East Hope Group Co., Ltd, Shanghai, China
Optimizing EEG Graph Structure for Seizure Detection: An Information Bottleneck and Self-Supervised Learning Approach
Apr 2, 2026Lincan Li, Rikuto Kotoge, Xihao Piao +2EEG Seizure Detection Graph Structure Learning
Department of Computer Science, Florida State University, Tallahassee, USA · SANKEN, The University of Osaka, Ibaraki, Japan
Dynamic Graph Neural Network with Adaptive Features Selection for RGB-D Based Indoor Scene Recognition
Apr 1, 2026Qiong Liu, Ruofei Xiong, Xingzhen Chen +2Multimodal Graph Learning Dynamic Graph Learning
School of Electronic Information and Communications, Huazhong University of Science and Technology, No. 1037, Luoyu Rd., Wuhan, 430074, P. R. China
Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphs
Mar 31, 2026Yuxuan Liu, Wenchao Xu, Haozhao Wang +5Federated Graph Learning Dynamic Graph Learning
School of Information and Communication Engineering, University of Electronic Science and Technology of China, China · Division of Integrative Systems and Design, Hong Kong University of Science and Technology, China · School of Computer Science and Technology, Huazhong University of Science and Technology, China
Graph Vector Field: A Unified Framework for Multimodal Health Risk Assessment from Heterogeneous Wearable and Environmental Data Streams
Mar 30, 2026Silvano Coletti, Francesca FallucchiHigher-Order GNNs Dynamic Graph Learning
Universit`a degli Studi Guglielmo Marconi, Roma, Italy · Chelonia SA, Lugano, Switzerland
DyMRL: Dynamic Multispace Representation Learning for Multimodal Event Forecasting in Knowledge Graph
Mar 25, 2026Feng Zhao, Kangzheng Liu, Teng Peng +2Multimodal KGs Temporal KGs
Natural Language Processing and Knowledge Graph Lab, School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China · Centre for Learning, Teaching and Technology, The Education University of Hong Kong, Hong Kong SAR, China
Subspace Projection Methods for Fast Spectral Embeddings of Evolving Graphs
Mar 19, 2026Mohammad Eini, Abdullah Karaaslanli, Vassilis Kalantzis +1Spectral Methods Dynamic Graph Learning
IBM Research
A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions
Mar 15, 2026Yiming Lei, Qiannan Shen, Junhao SongFinancial Fraud Detection Spatiotemporal GNNs
Georgia Institute of Technology, Atlanta, GA, USA · Boston University, Boston, MA, USA · Imperial College London, London, UK
Node Role-Guided LLMs for Dynamic Graph Clustering
Mar 14, 2026Dongyuan Li, Ying Zhang, Yaozu Wu +1Graph Clustering Dynamic Graph Learning
The University of Tokyo Tokyo, Japan · RIKEN Sendai, Japan
BrainSTR: Spatio-Temporal Contrastive Learning for Interpretable Dynamic Brain Network Modeling
Mar 10, 2026Guiliang Guo, Guangqi Wen, Lingwen Liu +6Dynamic Functional Connectivity Brain Network Analysis
Computer Science and Engineering, Northeastern University, Shenyang, China · School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan, China · Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Fukuoka, Japan +3
Detecting Fake Reviewer Groups in Dynamic Networks: An Adaptive Graph Learning Method
Mar 9, 2026Jing Zhang, Ke Huang, Yao Zhang +2Dynamic Graph Learning Anomaly Detection
School of Computer Science and Technology, Xi’an University of Science and Technology, Xi’an 710600, China · School of Computer Science, Northwestern Polytechnical University, Xi’an 710021, China · Harbin Engineering University, Harbin, Heilongjiang, China, and also with the School of Computer Science, Northwestern Polytechnical University, Xi’an, Shaanxi, China
Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution
Mar 9, 2026Hua Liu, Yanbin Wei, Fei Xing +3Dynamic Graph Learning Temporal Link Prediction
Southern University of Science and Technology · The Hong Kong University of Science and Technology · City University of Hong Kong +2
Polarized Direct Cross-Attention Message Passing in GNNs for Machinery Fault Diagnosis
Mar 6, 2026Zongyu Shi, Laibin Zhang, Maoyin ChenGraph Neural Networks Fault Diagnosis
Department of Automation, College of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102299, China · Department of Safety Engineering, College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102299, China
Random Dot Product Graphs as Dynamical Systems: Limitations and Opportunities
Mar 5, 2026Giulio Valentino Dalla RivaLatent Dynamics Modeling Dynamic Graph Learning
TFWaveFormer: Temporal-Frequency Collaborative Multi-level Wavelet Transformer for Dynamic Link Prediction
Mar 4, 2026Hantong Feng, Yonggang Wu, Duxin Chen +1Time-Frequency Analysis Temporal Link Prediction
School of Cyber Science and Engineering, Southeast University, Nanjing, China · School of Mathematics, Southeast University, Nanjing, China
How Predicted Links Influence Network Evolution: Disentangling Choice and Algorithmic Feedback in Dynamic Graphs
Mar 4, 2026Mathilde Perez, Raphaël Romero, Jefrey Lijffijt +1Hawkes Processes Social Network Analysis
LTCI, Télécom Paris, Institut Polytechnique de Paris, France. · IDLab , Ghent University , Belgium.
EEG-SeeGraph: Interpreting functional connectivity disruptions in dementias via sparse-explanatory dynamic EEG-graph learning
Mar 3, 2026Fengcheng Wu, Zhenxi Song, Guoyang Xu +4Electroencephalography Dynamic Graph Learning
Harbin Institute of Technology, Shenzhen, China · Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen · Institute of Neurological Diseases, Shenzhen Bay Laboratory, Shenzhen, China
Towards OOD Generalization in Dynamic Graphs via Causal Invariant Learning
Mar 2, 2026Xinxun Zhang, Pengfei Jiao, Mengzhou Gao +2OOD Generalization Dynamic Graph Learning
School of Cyberspace, Hangzhou Dianzi University, China · State Key Laboratory of AI Safety, Beijing · School of Computer Science, Wuhan University, China +1
Fed-GAME: Personalized Federated Learning with Graph Attention Mixture-of-Experts For Time-Series Forecasting
Mar 2, 2026Yi Li, Han Liu, Mingfeng Fan +3Federated Learning Federated Graph Learning
School of Automation, Central South University · Department of Electrical and Computer Engineering, National University of Singapore · Department of Mechanical Engineering, National University of Singapore +2
DWAFM: Dynamic Weighted Graph Structure Embedding Integrated with Attention and Frequency-Domain MLPs for Traffic Forecasting
Mar 1, 2026Sen Shi, Zhichao Zhang, Yangfan HeTraffic Forecasting Spatiotemporal Forecasting
School of Mathematics and Statistics, Nanjing University of Information Science and Technology, Nanjing 210044, China · Hubei Key Laboratory of Applied Mathematics, Hubei University, Wuhan 430062, China · Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai Jiao Tong University, Shanghai 200240, China +2
An Analysis of Role Semantics in Directed Dynamic Graph Modeling for Edge Classification
Feb 26, 2026Tyler Bonnet, Marek ReiGraph Representation Learning Self-Supervised Pre-Training
Imperial College London
Learning Disease-Sensitive Latent Interaction Graphs From Noisy Cardiac Flow Measurements
Feb 26, 2026Viraj Patel, Marko Grujic, Philipp Aigner +4Graph Structure Learning Physics-Informed GNNs
Department of Computer Science, University of Bath, Bath, UK · Christian Doppler Laboratory for Mechanical Circulatory Support, Department of Cardiac and Thoracic Aortic Surgery, Medical University of Vienna, Vienna, Austria · Department of Mechanical Engineering, University of Bath, Bath, UK
Coarse-to-Fine Learning of Dynamic Causal Structures
Feb 26, 2026Dezhi Yang, Qiaoyu Tan, Carlotta Domeniconi +3Time-Series Causal Discovery Causal Structure Learning
School of Software Shandong University Jinan, China · Department of Computer Science New York University Shanghai, China · Department of Computer Science George Mason University VA, USA +1
CGSTA: Cross-Scale Graph Contrast with Stability-Aware Alignment for Multivariate Time-Series Anomaly Detection
Feb 24, 2026Zhongpeng Qi, Jun Zhang, Wei Li +1Time-Series Anomaly Detection Graph Contrastive Learning
Dalian Maritime University, Dalian, China · Harbin Engineering University, Harbin, China
Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision
Feb 23, 2026Yuxing Tian, Yiyan Qi, Fengran Mo +3Semi-Supervised Anomaly Detection Graph-Based Anomaly Detection
Universit´e de Montréal · International Digital Economy Academy (IDEA) · McGill University +1
A Hybrid TGN-SEAL Model for Dynamic Graph Link Prediction
Feb 15, 2026Nafiseh Sadat Sajadi, Behnam Bahrak, Mahdi Jafari SiavoshaniTemporal GNNs Link Prediction
Department of Computer Engineering, Sharif University of Technology, Tehran, Iran. · Tehran Institute for Advanced Studies, Khatam University, Tehran, Iran.
What Do Temporal Graph Learning Models Learn?
Oct 10, 2025Abigail J. Hayes, Tobias Schumacher, Markus StrohmaierTemporal GNNs Temporal Link Prediction
University of Mannheim · RWTH Aachen University · GESIS - Leibniz Institute for the Social Sciences +1
Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
Aug 20, 2025Jiafeng Xiong, Rizos SakellariouGraph Structure Learning Temporal GNNs
Department of Computer Science, University of Manchester, UK
BrainATCL: Adaptive Temporal Brain Connectivity Learning for Functional Link Prediction and Age Estimation
Aug 9, 2025Yiran Huang, Amirhossein Nouranizadeh, Christine Ahrends +1Functional Connectivity Temporal GNNs
New Jersey Institute of Technology · University of Oxford
Efficient Traffic State Prediction With Dynamic Joint Spatio-Temporal Relation Inference
Apr 10, 2025Zhifeng Hao, Kai Hu, Juncai Zhang +2Temporal Convolutional Networks Dynamic Graph Learning
School of Cyberspace Security, Hainan University, Haikou, China

Apr 8, 2026J/K move · Enter open · S save

DSPR: Dual-Stream Physics-Residual Networks for Trustworthy Industrial Time Series Forecasting

Yeran Zhang, Pengwei Yang, Guoqing Wang, Tianyu Li

School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China · Research Center, East Hope Group Co., Ltd, Shanghai, China

Time Series Forecasting Multivariate Time Series Forecasting Non-Stationary Time Series Forecasting Physics-Informed ML Explainable Time Series Forecasting Dynamic Graph Learning

Open paper AskPDF arXiv

Accurate forecasting of industrial time series requires balancing predictive accuracy with physical plausibility under non-stationary operating conditions. Existing data-driven models often achieve strong statistical performance but struggle to respect regime-dependent interaction structures and transport delays inherent in real-world systems. To address this challenge, we propose DSPR (Dual-Stream Physics-Residual Networks), a forecasting framework that explicitly decouples stable temporal patterns from regime-dependent residual dynamics. The first stream models the statistical temporal evolution of individual variables. The second stream focuses on residual dynamics through two key mechanisms: an Adaptive Window module that estimates flow-dependent transport delays, and a Physics-Guided Dynamic Graph that incorporates physical priors to learn time-varying interaction structures while suppressing spurious correlations. Experiments on four industrial benchmarks spanning heterogeneous regimes demonstrate that DSPR consistently improves forecasting accuracy and robustness under regime shifts while maintaining strong physical plausibility. It achieves state-of-the-art predictive performance, with Mean Conservation Accuracy exceeding 99% and Total Variation Ratio reaching up to 97.2%. Beyond forecasting, the learned interaction structures and adaptive lags provide interpretable insights that are consistent with known domain mechanisms, such as flow-dependent transport delays and wind-to-power scaling behaviors. These results suggest that architectural decoupling with physics-consistent inductive biases offers an effective path toward trustworthy industrial time-series forecasting. Furthermore, DSPR's demonstrated robust performance in long-term industrial deployment bridges the gap between advanced forecasting models and trustworthy autonomous control systems.