ReInform: Selecting paths with reinforcement learning for contextualized link prediction
This work addresses link prediction in knowledge graphs, offering incremental improvements for researchers in AI and data mining.
The paper tackles the problem of improving contextualized link prediction by using reinforcement learning to select informative paths, resulting in up to 13.5% MRR gains on WN18RR and FB15k-237 datasets compared to RL-based answer search.
We propose to use reinforcement learning to inform transformer-based contextualized link prediction models by providing paths that are most useful for predicting the correct answer. This is in contrast to previous approaches, that either used reinforcement learning (RL) to directly search for the answer, or based their prediction on limited or randomly selected context. Our experiments on WN18RR and FB15k-237 show that contextualized link prediction models consistently outperform RL-based answer search, and that additional improvements (of up to 13.5% MRR) can be gained by combining RL with a link prediction model. The PyTorch implementation of the RL agent is available at https://github.com/marina-sp/reinform