Learning to Build Solutions in Stochastic Matching Problems Using Flows (Student Abstract)

William St-Arnaud, Margarida Carvalho, Golnoosh Farnadi

AAAI 2024 pp. 23659-23660

doi:10.1609/AAAI.V38I21.30515 /aaai/2024/starnaud2024aaai-learning/

Abstract

Generative Flow Networks, known as GFlowNets, have been introduced in recent times, presenting an exciting possibility for neural networks to model distributions across various data structures. In this paper, we broaden their applicability to encompass scenarios where the data structures are optimal solutions of a combinatorial problem. Concretely, we propose the use of GFlowNets to learn the distribution of optimal solutions for kidney exchange problems (KEPs), a generalized form of matching problems involving cycles.

PDF AAAI Semantic Scholar

Cite

Text

St-Arnaud et al. "Learning to Build Solutions in Stochastic Matching Problems Using Flows (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30515

Markdown

[St-Arnaud et al. "Learning to Build Solutions in Stochastic Matching Problems Using Flows (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/starnaud2024aaai-learning/) doi:10.1609/AAAI.V38I21.30515

BibTeX

@inproceedings{starnaud2024aaai-learning,
  title     = {{Learning to Build Solutions in Stochastic Matching Problems Using Flows (Student Abstract)}},
  author    = {St-Arnaud, William and Carvalho, Margarida and Farnadi, Golnoosh},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23659-23660},
  doi       = {10.1609/AAAI.V38I21.30515},
  url       = {https://mlanthology.org/aaai/2024/starnaud2024aaai-learning/}
}