Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings

Abstract

Asymmetrical distance structures (quasimetrics) are ubiquitous in our lives and are gaining more attention in machine learning applications. Imposing such quasimetric structures in model representations has been shown to improve many tasks, including reinforcement learning (RL) and causal relation learning. In this work, we present four desirable properties in such quasimetric models, and show how prior works fail at them. We propose Interval Quasimetric Embedding (IQE), which is designed to satisfy all four criteria. On three quasimetric learning experiments, IQEs show strong approximation and generalization abilities, leading to better performance and improved efficiency over prior methods.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Wang and Isola. "Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings." NeurIPS 2022 Workshops: NeurReps, 2022.

Markdown

[Wang and Isola. "Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings." NeurIPS 2022 Workshops: NeurReps, 2022.](https://mlanthology.org/neuripsw/2022/wang2022neuripsw-improved/)

BibTeX

@inproceedings{wang2022neuripsw-improved,
  title     = {{Improved Representation of Asymmetrical Distances with Interval Quasimetric Embeddings}},
  author    = {Wang, Tongzhou and Isola, Phillip},
  booktitle = {NeurIPS 2022 Workshops: NeurReps},
  year      = {2022},
  url       = {https://mlanthology.org/neuripsw/2022/wang2022neuripsw-improved/}
}