Yan Zhang

Aristide Baratin

Francesco Locatello

Irina Rish

Dianbo Liu

Kenji Kawaguchi

2024-07-08

Proceedings of the 41st International Conference on Machine Learning (published)

Alexia Jolicoeur-Martineau

PopulAtion Parameter Averaging (PAPA)

Emy Gervais

Kilian FATRAS

2024-04-05

TMLR (accepted)

Object centric architectures enable efficient causal representation learning

Amin Mansouri

Jason Hartford

Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees… (see more) (up to some reasonable equivalence class). Common to all of these approaches is the assumption that (1) the latent variables are represented as

2024-01-16

ICLR.cc/2024/Conference (poster)

Object-centric architectures enable efficient causal representation learning

Amin Mansouri

Jason Hartford

Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees… (see more) (up to some reasonable equivalence class). Common to all of these approaches is the assumption that (1) the latent variables are represented as

2023-10-29

ArXiv (preprint)

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

Jihye Kim

Aristide Baratin

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label cor… (see more)rection and co-teaching methods, we propose a novel training procedure to mitigate the memorization of noisy labels, called CrossSplit, which uses a pair of neural networks trained on two disjoint parts of the labeled dataset. CrossSplit combines two main ingredients: (i) Cross-split label correction. The idea is that, since the model trained on one part of the data cannot memorize example-label pairs from the other part, the training labels presented to each network can be smoothly adjusted by using the predictions of its peer network; (ii) Cross-split semi-supervised training. A network trained on one part of the data also uses the unlabeled inputs of the other part. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and mini-WebVision datasets demonstrate that our method can outperform the current state-of-the-art in a wide range of noise ratios. The project page is at https://rlawlgul.github.io/.

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

Equivariance with Learned Canonicalization Functions

Sékou-Oumar Kaba

Arnab Kumar Mondal

Siamak Ravanbakhsh

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

Unlocking Slot Attention by Changing Optimal Transport Costs

David W Zhang

Gertjan J. Burghouts

Cees G. M. Snoek

Slot attention is a powerful method for object-centric modeling in images and videos. However, its set-equivariance limits its ability to ha… (see more)ndle videos with a dynamic number of objects because it cannot break ties. To overcome this limitation, we first establish a connection between slot attention and optimal transport. Based on this new perspective we propose **MESH** (Minimize Entropy of Sinkhorn): a cross-attention module that combines the tiebreaking properties of unregularized optimal transport with the speed of regularized optimal transport. We evaluate slot attention using MESH on multiple object-centric learning benchmarks and find significant improvements over slot attention in every setting.

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

Equivariance With Learned Canonicalization Functions

Sékou-Oumar Kaba

Arnab Kumar Mondal

Siamak Ravanbakhsh

Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations… (see more). In this paper, we propose an alternative that avoids this architectural constraint by learning to produce a canonical representation of the data. These canonicalization functions can readily be plugged into non-equivariant backbone architectures. We offer explicit ways to implement them for many groups of interest. We show that this approach enjoys universality while providing interpretable insights. Our main hypothesis is that learning a neural network to perform canonicalization is better than doing it using predefined heuristics. Our results show that learning the canonicalization function indeed leads to better results and that the approach achieves great performance in practice.

2023-04-24

ICML.cc/2023/Conference (poster)

Alexia Jolicoeur-Martineau

PopulAtion Parameter Averaging (PAPA)

Emy Gervais

Kilian FATRAS

Ensemble methods combine the predictions of multiple models to improve performance, but they require significantly higher computation costs … (see more)at inference time. To avoid these costs, multiple neural networks can be combined into one by averaging their weights. However, this usually performs significantly worse than ensembling. Weight averaging is only beneficial when different enough to benefit from combining them, but similar enough to average well. Based on this idea, we propose PopulAtion Parameter Averaging (PAPA): a method that combines the generality of ensembling with the efficiency of weight averaging. PAPA leverages a population of diverse models (trained on different data orders, augmentations, and regularizations) while slowly pushing the weights of the networks toward the population average of the weights. We also propose PAPA variants (PAPA-all, and PAPA-2) that average weights rarely rather than continuously; all methods increase generalization, but PAPA tends to perform best. PAPA reduces the performance gap between averaging and ensembling, increasing the average accuracy of a population of models by up to 0.8% on CIFAR-10, 1.9% on CIFAR-100, and 1.6% on ImageNet when compared to training independent (non-averaged) models.

2023-04-06

ArXiv (preprint)

Alexia Jolicoeur-Martineau

PopulAtion Parameter Averaging (PAPA)

Emy Gervais

Kilian FATRAS

Ensemble methods combine the predictions of multiple models to improve performance, but they require significantly higher computation costs … (see more)at inference time. To avoid these costs, multiple neural networks can be combined into one by averaging their weights. However, this usually performs significantly worse than ensembling. Weight averaging is only beneficial when different enough to benefit from combining them, but similar enough to average well. Based on this idea, we propose PopulAtion Parameter Averaging (PAPA): a method that combines the generality of ensembling with the efficiency of weight averaging. PAPA leverages a population of diverse models (trained on different data orders, augmentations, and regularizations) while slowly pushing the weights of the networks toward the population average of the weights. We also propose PAPA variants (PAPA-all, and PAPA-2) that average weights rarely rather than continuously; all methods increase generalization, but PAPA tends to perform best. PAPA reduces the performance gap between averaging and ensembling, increasing the average accuracy of a population of models by up to 0.8% on CIFAR-10, 1.9% on CIFAR-100, and 1.6% on ImageNet when compared to training independent (non-averaged) models.

2023-04-06

ArXiv (preprint)

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

Jihye Kim

Aristide Baratin

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label cor… (see more)rection and co-teaching methods, we propose a novel training procedure to mitigate the memorization of noisy labels, called CrossSplit, which uses a pair of neural networks trained on two disjoint parts of the labelled dataset. CrossSplit combines two main ingredients: (i) Cross-split label correction. The idea is that, since the model trained on one part of the data cannot memorize example-label pairs from the other part, the training labels presented to each network can be smoothly adjusted by using the predictions of its peer network; (ii) Cross-split semi-supervised training. A network trained on one part of the data also uses the unlabeled inputs of the other part. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and mini-WebVision datasets demonstrate that our method can outperform the current state-of-the-art in a wide range of noise ratios.

2022-12-03

ArXiv (preprint)