Congrat: Self-supervised contrastive pretraining for joint graph and text embeddings
Learning on text-attributed graphs (TAGs), in which nodes are associated with one or more
texts, has been the subject of much recent work. However, most approaches tend to make …
texts, has been the subject of much recent work. However, most approaches tend to make …
Answering visual-relational queries in web-extracted knowledge graphs
A visual-relational knowledge graph (KG) is a multi-relational graph whose entities are
associated with images. We explore novel machine learning approaches for answering …
associated with images. We explore novel machine learning approaches for answering …
Learning representations of social media users
A Benton - arXiv preprint arXiv:1812.00436, 2018 - arxiv.org
User representations are routinely used in recommendation systems by platform developers,
targeted advertisements by marketers, and by public policy researchers to gauge public …
targeted advertisements by marketers, and by public policy researchers to gauge public …
Exploiting Latent Features of Text and Graphs
J Sybrandt - 2020 - search.proquest.com
As the size and scope of online data continues to grow, new machine learning techniques
become necessary to best capitalize on the wealth of available information. However, the …
become necessary to best capitalize on the wealth of available information. However, the …