Improving Temporal Knowledge Graph Forecasting via Multi-Rewards Mechanism and Confidence-Guided Tensor Decomposition Reinforcement Learning

Nam Le, Nam Le, Thanh Le, Thanh Le, Bac Le, Bac Le

2025

Abstract

Temporal knowledge graph reasoning, which has received widespread attention in the knowledge graph research community, is a task that predicts missing facts in data. When framed as a problem of forecasting future events, it becomes more challenging than the conventional completion task. Reinforcement learning is one of the potential techniques to address these challenges. Specifically, an agent navigates through a historical snapshot of a knowledge graph to find answers to the input query. However, these learning frameworks suffer from two main drawbacks: (1) a simplistic reward function and (2) candidate action selection being influenced by data sparsity issues. To address these problems, we propose a multi-reward function that integrates binary, adjusted path-based, adjusted ground truth-based, and high-frequency rule rewards to enhance the agent’s performance. Furthermore, we incorporate recent advanced tensor decomposition methods such as TuckER, ComplEx, and LowFER to construct a reliability evaluation module for candidate actions, allowing the agent to make more reliable action choices. Our empirical results on benchmark datasets demonstrate significant improvements in performance while preserving computational efficiency and requiring fewer trainable parameters.

Paper Citation

in Harvard Style

Le N., Le T. and Le B. (2025). Improving Temporal Knowledge Graph Forecasting via Multi-Rewards Mechanism and Confidence-Guided Tensor Decomposition Reinforcement Learning. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 68-79. DOI: 10.5220/0013161400003890

in Bibtex Style

@conference{icaart25,
author={Nam Le and Thanh Le and Bac Le},
title={Improving Temporal Knowledge Graph Forecasting via Multi-Rewards Mechanism and Confidence-Guided Tensor Decomposition Reinforcement Learning},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART},
year={2025},
pages={68-79},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013161400003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART
TI - Improving Temporal Knowledge Graph Forecasting via Multi-Rewards Mechanism and Confidence-Guided Tensor Decomposition Reinforcement Learning
SN - 978-989-758-737-5
AU - Le N.
AU - Le T.
AU - Le B.
PY - 2025
SP - 68
EP - 79
DO - 10.5220/0013161400003890
PB - SciTePress