Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning

TL;DR

This paper introduces a novel full-history graph representation and an Edge-Type Decoupled Network (ETDNet) for improved temporal reasoning in dynamic interaction modeling, outperforming existing methods in traffic and fraud detection tasks.

Contribution

The paper proposes a full-history graph with separate intra- and inter-time-step edges and a new ETDNet architecture that effectively combines structural and temporal information.

Findings

ETDNet achieves higher accuracy in driver intention prediction.

ETDNet significantly improves fraud detection F1 scores.

The approach demonstrates the advantage of decoupling structural and temporal edges.

Abstract

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.