Masked autoencoder (MAE), a simple and effective self-supervised learning framework based on the reconstruction of masked image regions, has recently achieved prominent …
Y Mo, Y Lei, J Shen, X Shi… - … on Machine Learning, 2023 - proceedings.mlr.press
Unsupervised multiplex graph representation learning (UMGRL) has received increasing interest, but few works simultaneously focused on the common and private information …
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially …
Contrastive learning is a cornerstone underlying recent progress in multi-view and multimodal learning, eg, in representation learning with image/caption pairs. While its …
Identifying latent variables and causal structures from observational data is essential to many real-world applications involving biological data, medical data, and unstructured data …
Recently, various methods have been introduced to address the OOD detection problem with training outlier exposure. These methods usually count on discriminative softmax metric …
Self-supervised representation learning often uses data augmentations to induce some invariance to" style" attributes of the data. However, with downstream tasks generally …
In recent years, deep learning approaches have gained significant attention in predicting brain disorders using neuroimaging data. However, conventional methods often rely on …