Publications

Continuous normalizing ﬂows (CNFs) are an attractive generative modeling technique, but they have thus far been held back by limitations i… (see more)n their simulation-based maximum likelihood training. In this paper, we introduce a new technique called conditional ﬂow matching (CFM), a simulation-free training objective for CNFs. CFM features a stable regression objective like that used to train the stochastic ﬂow in diffusion models but enjoys the efﬁcient inference of deterministic ﬂow models. In contrast to both diffusion models and prior CNF training algorithms, our CFM objec-tive does not require the source distribution to be Gaussian or require evaluation of its density. Based on this new objective, we also introduce optimal transport CFM (OT-CFM), which creates simpler ﬂows that are more stable to train and lead to faster inference, as evaluated in our experiments. Training CNFs with CFM improves results on a variety of conditional and unconditional generation tasks such as inferring single cell dynamics, unsupervised image translation, and Schr ¨ odinger bridge inference. Code is available at https://github.com/atong01/ conditional-flow-matching .

2023-01-01

arXiv.org (preprint)

doi.org

Constant Memory Attentive Neural Processes

Leo Feng

Frederick Tung

Hossein Hajimirsadeghi

Yoshua Bengio

Mohamed Osama Ahmed

2023-01-01

arXiv.org (preprint)

doi.org

Continually learning representations at scale

Alexandre Galashov

Jovana Mitrovic

Dhruva Tirumala

Yee Whye Teh

Timothy Nguyen

Arslan Chaudhry

Razvan Pascanu

2023-01-01

CoLLAs (published)

proceedings.mlr.press

Contrast-agnostic deep learning–based registration pipeline: Validation in spinal cord multimodal MRI data

E. Beal

Julien Cohen-Adad

2023-01-01

Aperture Neuro (published)

doi.org

Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Fine-grained Understanding

Le Zhang

Rabiul Awal

Aishwarya Agrawal

2023-01-01

arXiv.org (preprint)

doi.org

Contrastive Positive Unlabeled Learning

Anish Acharya

Sujay Sanghavi

Li Jing

Bhargav Bhushanam

Michael Rabbat

I. Dhillon

Self-supervised pretraining on unlabeled data followed by supervised fine-tuning on labeled data is a popular paradigm for learning from lim… (see more)ited labeled examples. We extend this paradigm to the classical positive unlabeled (PU) setting, where the task is to learn a binary classifier given only a few labeled positive samples, and (often) a large amount of unlabeled samples (which could be positive or negative). We first propose a simple extension of standard infoNCE family of contrastive losses, to the PU setting; and show that this learns superior representations, as compared to existing unsupervised and supervised approaches. We then develop a simple methodology to pseudo-label the unlabeled samples using a new PU-specific clustering scheme; these pseudo-labels can then be used to train the final (positive vs. negative) classifier. Our method handily outperforms state-of-the-art PU methods over several standard PU benchmark datasets, while not requiring a-priori knowledge of any class prior (which is a common assumption in other PU methods). We also provide a simple theoretical analysis that motivates our methods.

Leveraging AI for a Sustainable Future

Mila AI Policy Fellowship

Hugo Larochelle appointed Scientific Director of Mila

Publications

Leveraging AI for a Sustainable Future

Mila AI Policy Fellowship

Hugo Larochelle appointed Scientific Director of Mila

Popular keywords:

Publications