Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to
advance machine learning. Yet, much like cooking, training SSL methods is a delicate art …

Recent approximations to backpropagation (BP) have mitigated many of BP's computational
inefficiencies and incompatibilities with biology, but important limitations still remain …

Recent progress has been made towards learning invariant or equivariant representations
with self-supervised learning. While invariant methods are evaluated on large scale …

Hebbian plasticity in winner-take-all (WTA) networks is highly attractive for neuromorphic on-
chip learning, owing to its efficient, local, unsupervised, and on-line nature. Moreover, its …

Self-supervised learning is a popular and powerful method for utilizing large amounts of
unlabeled data, for which a wide variety of training objectives have been proposed in the …

We identify sufficient conditions to avoid known failure modes, including representation,
dimensional, cluster and intracluster collapses, occurring in non-contrastive self-supervised …

We propose PseudoNeg-MAE, a novel self-supervised learning framework that enhances
global feature representation of point cloud mask autoencoder by making them both …

Collaborative Filtering (CF) models based on Graph Contrastive Learning (GCL) have
effectively improved the performance of long-tail recommendation. However, the popularity …

Self-supervised learning is a popular and powerful method for utilizing large amounts of
unlabeled data, for which a wide variety of training objectives have been proposed in the …

Self-supervised learning excels at learning representations from large amounts of data. At
the same time, generative models offer the complementary property of learning information …