Contrasting Multiple Representations with the Multi-Marginal Matching Gap

Zoe Piran, Michal Klein, James Thornton, Marco Cuturi
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40827-40842, 2024.

Abstract

Learning meaningful representations of complex objects that can be seen through multiple (k≥3) views or modalities is a core task in machine learning. Existing methods use losses originally intended for paired views, and extend them to k views, either by instantiating 12k(k−1) loss-pairs, or by using reduced embeddings, following a one vs. average-of-rest strategy. We propose the multi-marginal matching gap (M3G), a loss that borrows tools from multi-marginal optimal transport (MM-OT) theory to simultaneously incorporate all k views. Given a batch of n points, each seen as a k-tuple of views subsequently transformed into k embeddings, our loss contrasts the cost of matching these n ground-truth k-tuples with the MM-OT polymatching cost, which seeks n optimally arranged k-tuples chosen within these n×k vectors. While the exponential complexity O(nk) of the MM-OT problem may seem daunting, we show in experiments that a suitable generalization of the Sinkhorn algorithm for that problem can scale to, e.g., k=3∼6 views using mini-batches of size 64∼128. Our experiments demonstrate improved performance over multiview extensions of pairwise losses, for both self-supervised and multimodal tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-piran24a, title = {Contrasting Multiple Representations with the Multi-Marginal Matching Gap}, author = {Piran, Zoe and Klein, Michal and Thornton, James and Cuturi, Marco}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {40827--40842}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/piran24a/piran24a.pdf}, url = {https://proceedings.mlr.press/v235/piran24a.html}, abstract = {Learning meaningful representations of complex objects that can be seen through multiple ($k\geq 3$) views or modalities is a core task in machine learning. Existing methods use losses originally intended for paired views, and extend them to $k$ views, either by instantiating $\tfrac12k(k-1)$ loss-pairs, or by using reduced embeddings, following a one vs. average-of-rest strategy. We propose the multi-marginal matching gap (M3G), a loss that borrows tools from multi-marginal optimal transport (MM-OT) theory to simultaneously incorporate all $k$ views. Given a batch of $n$ points, each seen as a $k$-tuple of views subsequently transformed into $k$ embeddings, our loss contrasts the cost of matching these $n$ ground-truth $k$-tuples with the MM-OT polymatching cost, which seeks $n$ optimally arranged $k$-tuples chosen within these $n\times k$ vectors. While the exponential complexity $O(n^k$) of the MM-OT problem may seem daunting, we show in experiments that a suitable generalization of the Sinkhorn algorithm for that problem can scale to, e.g., $k=3\sim 6$ views using mini-batches of size $64 \sim128$. Our experiments demonstrate improved performance over multiview extensions of pairwise losses, for both self-supervised and multimodal tasks.} }
Endnote
%0 Conference Paper %T Contrasting Multiple Representations with the Multi-Marginal Matching Gap %A Zoe Piran %A Michal Klein %A James Thornton %A Marco Cuturi %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-piran24a %I PMLR %P 40827--40842 %U https://proceedings.mlr.press/v235/piran24a.html %V 235 %X Learning meaningful representations of complex objects that can be seen through multiple ($k\geq 3$) views or modalities is a core task in machine learning. Existing methods use losses originally intended for paired views, and extend them to $k$ views, either by instantiating $\tfrac12k(k-1)$ loss-pairs, or by using reduced embeddings, following a one vs. average-of-rest strategy. We propose the multi-marginal matching gap (M3G), a loss that borrows tools from multi-marginal optimal transport (MM-OT) theory to simultaneously incorporate all $k$ views. Given a batch of $n$ points, each seen as a $k$-tuple of views subsequently transformed into $k$ embeddings, our loss contrasts the cost of matching these $n$ ground-truth $k$-tuples with the MM-OT polymatching cost, which seeks $n$ optimally arranged $k$-tuples chosen within these $n\times k$ vectors. While the exponential complexity $O(n^k$) of the MM-OT problem may seem daunting, we show in experiments that a suitable generalization of the Sinkhorn algorithm for that problem can scale to, e.g., $k=3\sim 6$ views using mini-batches of size $64 \sim128$. Our experiments demonstrate improved performance over multiview extensions of pairwise losses, for both self-supervised and multimodal tasks.
APA
Piran, Z., Klein, M., Thornton, J. & Cuturi, M.. (2024). Contrasting Multiple Representations with the Multi-Marginal Matching Gap. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:40827-40842 Available from https://proceedings.mlr.press/v235/piran24a.html.

Related Material