Forecasting Interaction Order on Temporal Graphs
Explore this paper's citation graph
Summary
A graph neural network model named Temporal ATtention network (TAT) is developed, which utilizes the fine-grained time information on temporal graphs by encoding continuous real-valued timestamps as vectors and proposes a novel training scheme to address the permutation-sensitive property of the problem.
- Type
- article
- Published
- 2021-08-14
- Cited by
- 10
- References
- 49
- Access
- Open access
- OpenAlex
- https://openalex.org/W3170430684
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:236980253
Keywords
Computer science, Theoretical computer science, Timestamp, Binary number, Graph
References
- Evidence for a bimodal distribution in human communication
- Link Prediction in Complex Networks: A Survey
- Transaction network analysis for studying Local Exchange Trading Systems (LETS): Research potentials and limitations
- Graph evolution: Densification and shrinking diameters
- Human-level control through deep reinforcement learning
- On the evolution of user interaction in Facebook
- Memory in network flows and its effects on spreading dynamics and community detection
- An introduction to ROC analysis
- Molecular graph convolutions: moving beyond fingerprints
- Real-Time Influence Maximization on Dynamic Social Streams
- Dynamic Graph Convolutional Networks
- Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting
- Topology adaptive graph convolutional networks
- Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
- Simplicial closure and higher-order link prediction
- Representation Learning over Dynamic Graphs
- Continuous-Time Dynamic Network Embeddings
- Exploiting Structural and Temporal Evolution in Dynamic Link Prediction
- Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting
- DyRep: Learning Representations over Dynamic Graphs
Cited by
- Graph Neural Point Process for Temporal Interaction Prediction
- A Class-Aware Representation Refinement Framework for Graph Classification
- TPGNN: Learning High-order Information in Dynamic Graphs via Temporal Propagation
- Interaction Order Prediction for Temporal Graphs
- Temporal SIR-GN: Efficient and Effective Structural Representation Learning for Temporal Graphs
- Disentangling the Computational Complexity of Network Untangling
- Temporal Graph Contrastive Learning for Sequential Recommendation
- DGNN-MN: Dynamic Graph Neural Network via memory regenerate and neighbor propagation
- How to Avoid Jumping to Conclusions: Measuring the Robustness of Outstanding Facts in Knowledge Graphs
Related papers
- An algorithm for timestamp removal for panorama video surveillance
- A Lifelog System Specialized to Record Timestamp of Daily Works
- Efficient Timestamps for Capturing Causality
- Timestamp representations for virtual sequences
- A Comparative Study of Forecasting Problems on Electrical Load Timeseries Data using Deep Learning Techniques
- Distributed timestamp generation in planar lattice networks
- Intelligent Visual Surveillance with RFID Timestamp
- Detection of Malicious Node using Timestamp in USN Adapted Diffie-Hellman Algorithm