This shows you the differences between two versions of the page.
— |
papers:rame-2023 [2023/08/29 06:12] (current) leonb created |
||
---|---|---|---|
Line 1: | Line 1: | ||
+ | ===== Model Ratatouille: | ||
+ | // | ||
+ | solutions: from a pre-trained foundation model, | ||
+ | they fine-tune the weights on the target task of | ||
+ | interest. So, the Internet is swarmed by a handful | ||
+ | of foundation models fine-tuned on many diverse | ||
+ | tasks: these individual fine-tunings exist in isolation without benefiting from each other. In our | ||
+ | opinion, this is a missed opportunity, | ||
+ | In this paper, we thus propose model ratatouille, | ||
+ | a new strategy to recycle the multiple fine-tunings | ||
+ | of the same foundation model on diverse auxiliary tasks. Specifically, | ||
+ | fine-tunings on the target task; then, we average | ||
+ | all fine-tuned weights to obtain the final model. | ||
+ | This recycling strategy aims at maximizing the | ||
+ | diversity in weights by leveraging the diversity in | ||
+ | auxiliary tasks. Empirically, | ||
+ | of the art on the reference DomainBed benchmark | ||
+ | for out-of-distribution generalization. Looking | ||
+ | forward, this work contributes to the emerging | ||
+ | paradigm of updatable machine learning where, | ||
+ | akin to open-source software development, | ||
+ | community collaborates to reliably update machine learning models. Our code is released [[https:// | ||
+ | |||
+ | {{ ratatouille.png? | ||
+ | |||
+ | <box 99% orange> | ||
+ | Alexandre Rame, Kartik Ahuja, Jianyu Zhang, Matthieu Cord, Leon Bottou and David Lopez-Paz: | ||
+ | |||
+ | [[http:// | ||
+ | [[http:// | ||
+ | [[http:// | ||
+ | </ | ||
+ | |||
+ | @inproceedings{rame-2023, | ||
+ | title = {Model Ratatouille: | ||
+ | author = {Rame, Alexandre and Ahuja, Kartik and Zhang, Jianyu and Cord, Matthieu and Bottou, Leon and Lopez-Paz, David}, | ||
+ | booktitle = {Proceedings of the 40th International Conference on Machine Learning}, | ||
+ | pages = {28656--28679}, | ||
+ | year = {2023}, | ||
+ | editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, | ||
+ | volume = {202}, | ||
+ | series = {Proceedings of Machine Learning Research}, | ||
+ | month = {23--29 Jul}, | ||
+ | publisher = {PMLR}, | ||
+ | url = {http:// | ||
+ | } |