Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have attracted increasing concerns.

This leads to a new MU paradigm, termed prune first, then unlearn, which infuses a sparse model prior into the unlearning process.

A central notion in practical and theoretical machine learning is that of a weak learner, classifiers that achieve better-than-random performance (on any given distribution over data), even by a small margin. Such weak learners form the practical basis for canonical machine learning methods such as boosting.

Standard few-shot learning methods employ geometric similarity metrics such as cosine similarity and negative Euclidean distance to gauge the semantic relatedness between two features.

Standard few-shot learning methods employ geometric similarity metrics such as cosine similarity and negative Euclidean distance to gauge the semantic relatedness between two features.

Learning to detect and encode temporal regularities (TRs) in events is a prerequisite for human-like intelligence. These regularities should be formed from limited event samples and stored as easily retrievable representations.

Graph-structured data is ubiquitous in various disciplines [Gilmer et al., 2017, Zitnik et al., 2018, Sanchez-Gonzalez et al., 2020] and hence graph representation learning has the potential to provide