Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another over consecutive frames. Likewise, detecting financial fraud hinges on following the flow of funds through successive transactions as they propagate through the network. Unlike classic time-series forecasting, these settings demand reasoning over who interacts with whom and when, calling for a temporal-graph representation that makes both the relations and their evolution explicit. Existing temporal-graph methods typically use snapshot graphs to encode temporal evolution. We introduce a full-history graph that instantiates one node for every entity at every time step and separates two edge sets: (i) intra-time-step edges that capture relations within a single frame and (ii) inter-time-step edges that connect an entity to itself at consecutive steps. To learn on this graph we design an Edge-Type Decoupled Network (ETDNet) with parallel modules: a graph-attention module aggregates information along intra-time-step edges, a multi-head temporal-attention module attends over an entity's inter-time-step history, and a fusion module combines the two messages after every layer. Evaluated on driver-intention prediction (Waymo) and Bitcoin fraud detection (Elliptic++), ETDNet consistently surpasses strong baselines, lifting Waymo joint accuracy to 75.6% (vs. 74.1%) and raising Elliptic++ illicit-class F1 to 88.1% (vs. 60.4%). These gains demonstrate the benefit of representing structural and temporal relations as distinct edges in a single graph.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 25 of its 35 references that are in the map. First posted on arXiv 5 Aug 2025.
Builds on
25 of 35 references.
References · 25
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
- 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
- 2020Inductive Representation Learning on Temporal Graphscited by 462
- 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 448
- 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
- 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 164
- 2023Temporal Graph Benchmark for Machine Learning on Temporal Graphscited by 138
- 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 123
- 2021Accurate Learning of Graph Representations with Graph Multiset Poolingcited by 120
13 more
- 2020TeMP: Temporal Message Passing for Temporal Knowledge Graph Completioncited by 61
- 2023Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunitiescited by 61
- 2022Scalable Spatiotemporal Graph Neural Networkscited by 52
- 2022TREND: TempoRal Event and Node Dynamics for Graph Representation Learningcited by 50
- 2022Weisfeiler-Lehman goes Dynamic: An Analysis of the Expressive Power of Graph Neural Networks for Attributed and Dynamic Graphscited by 12
- 2024SemanticFormer: Holistic and Semantic Traffic Scene Representation for Trajectory Prediction using Knowledge Graphscited by 11
- 2019Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutionscited by 8
- 2021Graph Neural Networks for Traffic Forecastingcited by 7
- 2024Network Analytics for Anti-Money Laundering -- A Systematic Literature Review and Experimental Evaluationcited by 7
- 2023NeutronStream: A Dynamic GNN Training Framework with Sliding Window for Graph Streamscited by 6
- 2020GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregationcited by 1
- 2024TempoKGAT: A Novel Graph Attention Network Approach for Temporal Graph Analysiscited by 1
- 2024Mind the truncation gap: challenges of learning on dynamic graphs with recurrent architecturescited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025T-GRAB: A Synthetic Diagnostic Benchmark for Learning on Temporal Graphs
- 2024TimeGraphs: Graph-based Temporal Reasoning
- 2026TemporalGraphLLM: Temporal Graph Neural Networks with Large Language Models for Dynamic Text-Attributed Graphs
- 2026TRACE: Temporal Rule-Anchored Chain-of-Evidence on Knowledge Graphs for Interpretable Stock Movement Prediction
- 2025A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs
- 2024Transformer-based Reasoning for Learning Evolutionary Chain of Events on Temporal Knowledge Graph
- 2023GradXKG: A Universal Explain-per-use Temporal Knowledge Graph Explainer
- 2026Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context