Matrix sketching is a powerful tool for reducing the size of large data matrices.

The aim of this paper is to address the challenge of gradual domain adaptation within a class of manifold-constrained data distributions.

It is common to consider two encoders similar if they are homotopic, i.e., if they can be aligned through some transformation.

Concretely, we prove that polynomial-sized message-passing GNN's can learn the

Finally, we conclude by highlighting the significant applications of long-tailed learning and identifying several promising future directions.