AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning

TL;DR

AdaTKG introduces an adaptive memory mechanism for temporal knowledge graphs, enabling entity representations to evolve with each interaction, leading to improved reasoning over time.

Contribution

It proposes a novel adaptive memory approach that updates entity representations online, handling unseen entities and enhancing reasoning accuracy.

Findings

AdaTKG outperforms baseline models on multiple TKG reasoning tasks.

The adaptive memory improves entity representation quality over time.

Code is publicly available at https://github.com/seunghan96/AdaTKG.

Abstract

Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity representations that are static at the entity level, in that each representation is a function of learned parameters only and retains no trace of the interactions in which the entity has participated. In this paper, we depart from this static view and propose that each entity be modeled as an adaptive process whose representation is refined every time the entity participates in a fact. To this end, we propose AdaTKG, which maintains a per-entity memory that is updated with every observed interaction, with the memory accumulating online and predictions improving as more interactions arrive. Specifically, we instantiate the memory update as a learnable exponential moving average governed by a single shared scalar instead of using learnable parameters for each entity, enabling AdaTKG to handle entities unseen during training. Extensive experiments confirm consistent gains over TKG baselines, demonstrating the effectiveness of adaptive memory. Code is publicly available at: https://github.com/seunghan96/AdaTKG.