Publications

Crystal-GFlowNet: sampling materials with desirable properties and constraints. Mila AI4Science (*team name denoting the equal contribution of all authors*), Alex Hernández-García, Alexandra Volokhova, Alexandre Duval, Yoshua Bengio, Divya Sharma, Pierre Luc Carrier, Michał Koziarski, Victor Schmidt. Under review at NeurIPS AI4MAt workshop.. 2023. arXiv

On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions. Alvaro Carbonero, Alexandre Duval, Victor Schmidt, Santiago Miret, Alex Hernandez-Garcia, Yoshua Bengio, David Rolnick. Under submission at NeurIPS AI4MAt workshop.. 2023. arXiv

FAENet: Frame Averaging Equivariant GNNs for Materials Modeling. Alexandre Duval, Victor Schmidt, Santiago Miret, Yoshua Bengio, Alex Hernandez-Garcia, David Rolnick. International Conference on Machine Learning (ICML).. 2023. arXiv

PhAST: physics-aware, scalable, and task-specific GNNs for accelerated catalyst design. Alexandre Duval, Victor Schmidt, Santiago Miret, Yoshua Bengio, Alex Hernandez-Garcia, David Rolnick. Neural Information Processing Systems (NeurIPS), Workshop on Accelerated Materials Design (AI4Mat). Under review at JMLR.. 2022. arXiv OpenReview

Higher-order clustering and pooling for graph neural networks. Alexandre Duval, Fragkiskos D. Malliaros. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management (pp. 426-435).. 2022. arXiv

Graphsvx: Shapley value explanations for graph neural networks. Alexandre Duval, Fragkiskos D. Malliaros. In Machine Learning and Knowledge Discovery in Databases. Research Track, European Conference, ECML PKDD 2021, Bilbao, Spain, September 13–17, 2021, Proceedings, Part II 21 (pp. 302-318). Springer International Publishing.. 2021. arXiv

Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models. Alexandre Duval, Thomas Lamson, Gael d. L. de Kérouara, Matthias Gallé. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021). 2020. arXiv