Related papers: Contrastive Mixture of Posteriors for Counterfactu…

Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In the context of document classification under topic modeling…

Humans perceive the world through multisensory integration, blending the information of different modalities to adapt their behavior. Contrastive learning offers an appealing solution for multimodal self-supervised learning. Indeed, by…

Arbitrary conditioning is an important problem in unsupervised learning, where we seek to model the conditional densities $p(\mathbf{x}_u \mid \mathbf{x}_o)$ that underly some data, for all possible non-intersecting subsets $o, u \subset…

Variational autoencoders (VAEs) suffer from posterior collapse, where the powerful neural networks used for modeling and inference optimize the objective without meaningfully using the latent representation. We introduce inference critics…

Contrastive learning has emerged as a cornerstone in recent achievements of unsupervised representation learning. Its primary paradigm involves an instance discrimination task with a mutual information loss. The loss is known as InfoNCE and…

Learning representations that transfer well to diverse downstream tasks remains a central challenge in representation learning. Existing paradigms -- contrastive learning, self-supervised masking, and denoising auto-encoders -- balance this…

Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consistency (SC) assumption, which may not hold in unconstrained…

We introduce a new convexified matching method for missing value imputation and individualized inference inspired by computational optimal transport. Our method integrates favorable features from mainstream imputation approaches: optimal…

Learning joint representations across multiple modalities remains a central challenge in multimodal machine learning. Prevailing approaches predominantly operate in pairwise settings, aligning two modalities at a time. While some recent…

In recent years, several unsupervised, "contrastive" learning algorithms in vision have been shown to learn representations that perform remarkably well on transfer tasks. We show that this family of algorithms maximizes a lower bound on…

Mixture proportion estimation (MPE) aims to estimate class priors from unlabeled data. This task is a critical component in weakly supervised learning, such as PU learning, learning with label noise, and domain adaptation. Existing MPE…

This work aims efficiently estimating the posterior distribution of kinetic parameters for dynamic positron emission tomography (PET) imaging given a measurement of time of activity curve. Considering the inherent information loss from…

Contrastive Analysis is a sub-field of Representation Learning that aims at separating common factors of variation between two datasets, a background (i.e., healthy subjects) and a target (i.e., diseased subjects), from the salient factors…

Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation. By learning to contrast positive pairs' representation from the corresponding negatives pairs, one can train good visual…

Several automatic approaches for objective music performance assessment (MPA) have been proposed in the past, however, existing systems are not yet capable of reliably predicting ratings with the same accuracy as professional judges. This…

Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data. However, the learned representations could potentially lead to performance…

Reliable robot perception requires not only predicting scene structure, but also identifying where predictions should be treated as unreliable due to sparse or missing observations. We present ContraMap, a contrastive continuous mapping…

Contrastive learning has recently established itself as a powerful self-supervised learning framework for extracting rich and versatile data representations. Broadly speaking, contrastive learning relies on a data augmentation scheme to…

Estimating an individual's counterfactual outcomes under interventions is a challenging task for traditional causal inference and supervised learning approaches when the outcome is high-dimensional (e.g. gene expressions, facial images) and…

A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features. Extracting such task-relevant predictive…