Empathy and AI: Achieving Equitable Microtransit for Underserved Communities
Abstract
Graph contrastive learning (GCL) often suffers from false negatives, which degrades the performance on downstream tasks. The existing methods addressing the false negative issue usually rely on human prior knowledge, still leading GCL to suboptimal results. In this paper, we propose a novel Negative Metric Learning (NML) enhanced GCL (NML-GCL). NML-GCL employs a learnable Negative Metric Network (NMN) to build a negative metric space, in which false negatives can be distinguished better from true negatives based on their distance to anchor node. To overcome the lack of explicit supervision signals for NML, we propose a joint training scheme with bi-level optimization objective, which implicitly utilizes the self-supervision signals to iteratively optimize the encoder and the negative metric network. The solid theoretical analysis and the extensive experiments conducted on widely used benchmarks verify the superiority of the proposed method.
Cite
Text
Bardaka et al. "Empathy and AI: Achieving Equitable Microtransit for Underserved Communities." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/794Markdown
[Bardaka et al. "Empathy and AI: Achieving Equitable Microtransit for Underserved Communities." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/bardaka2024ijcai-empathy/) doi:10.24963/ijcai.2024/794BibTeX
@inproceedings{bardaka2024ijcai-empathy,
title = {{Empathy and AI: Achieving Equitable Microtransit for Underserved Communities}},
author = {Bardaka, Eleni and Van Hentenryck, Pascal and Lee, Crystal Chen and Mayhorn, Christopher B. and Monast, Kai and Samaranayake, Samitha and Singh, Munindar P.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {7179-7187},
doi = {10.24963/ijcai.2024/794},
url = {https://mlanthology.org/ijcai/2024/bardaka2024ijcai-empathy/}
}