Artificial Intelligence (cs.AI)

Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces. We …

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their …

Few-shot graph classification is a novel yet promising emerging research field that still lacks the soundness of well-established …

We introduce Explanatory Learning (EL), a framework to let machines use existing knowledge buried in symbolic sequences – e.g. …