Enhancing Temporal Knowledge Graph Completion with Global Similarity and Weighted Sampling

Mehrnoosh Mirtaheri, Ryan A. Rossi, Sungchul Kim, Kanak Mahadik, Xiang Chen, Tong Yu, Mohammad Rostami

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Temporal Knowledge Graph, Representation Learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: Model agnostic framework for improving temporal knowledge graph completion that leverages entities global similarities and weighted sampling

Abstract: Temporal Knowledge Graph (TKG) completion models traditionally assume access to the entire graph during training. This overlooks challenges stemming from the evolving nature of TKGs, such as: (i) the model's requirement to generalize and assimilate new knowledge, and (ii) the task of managing new or unseen entities that often have sparse connections. In this paper, we present an incremental training framework specifically designed for TKGs, aiming to address entities that are either not observed during training or have sparse connections. Our approach combines a model-agnostic enhancement layer with a weighted sampling strategy, that can be augmented to and improve any existing TKG completion method. The enhancement layer leverages a broader, global definition of entity similarity, moving beyond mere local neighborhood proximity of GNN-based methods. The weighted sampling strategy employed in training accentuates edges linked to infrequently occurring entities. Our evaluations, conducted on two benchmark datasets, demonstrate that our framework outperforms existing methods in overall link prediction, inductive link prediction, and in addressing long-tail entities. Notably, our method achieves a 10\% improvement in MRR for one dataset and a 15\% boost for another. The results underscore the potential of our approach in mitigating catastrophic forgetting and enhancing the robustness of TKG completion methods, especially in an incremental training context.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2926