Models of hyperbolic geometry have been successfully used to embed hierarchies, i.e. tree-based structures [

In recent years, semi-supervised learning (SSL) has gained significant attention due to its ability to leverage both labeled and unlabeled data to improve model performance, especially when labeled data is scarce. However, most current SSL methods rely on heuristics or predefined rules for generating pseudo-labels and leveraging unlabeled data.

Districting is a complex combinatorial problem that consists in partitioning a geographical area into small districts.

Contrastive learning has been a leading paradigm for self-supervised learning, but it is widely observed that it comes at the price of sacrificing useful features ( e.g., colors) by being invariant to data augmentations.

Softmax Loss (SL) is widely applied in recommender systems (RS) and has demonstrated effectiveness.

In label-noise learning, the noise transition matrix reveals how an instance transitions from its clean label to its noisy label. Accurately estimating an instance's noise transition matrix is crucial for estimating its clean label.

Can incorporating context into self-supervised vision algorithms eliminate augmentation-based inductive priors and enable dynamic adaptation to varying task symmetries? This work suggests a positive answer to this question by proposing to enhance the current joint embedding architecture with a finite context -- an abstract representation of a task, containing a few demonstrations that inform about task-specific symmetries, as shown in Figure 2(c).

Learning the intents of an agent, defined by its goals or motion style, is often extremely challenging from just a few examples.