Cross-Domain Relation Adaptation

Ido Kessler, Omri Lifshitz, Sagie Benaim, Lior Wolf

Research output: Contribution to journalConference articlepeer-review


We consider the challenge of establishing relationships between samples in distinct domains, A and B, using supervised data that captures the intrinsic relationships within each domain. In other words, we present a semi-supervised setting in which there are no labeled mixed-domain pairs of samples. Our method is derived based on a generalization bound and incorporates supervised terms for each domain, a domain confusion term on the learned features, and a consistency term for domain-specific relationships when considering mixed-domain sample pairs. Our findings showcase the efficacy of our approach in two disparate domains: (i) Predicting protein-protein interactions between viruses and hosts by modeling genetic sequences. (ii) Forecasting link connections within citation graphs using graph neural networks.

Original languageEnglish
Pages (from-to)630-645
Number of pages16
JournalProceedings of Machine Learning Research
StatePublished - 2023
Event15th Asian Conference on Machine Learning, ACML 2023 - Istanbul, Turkey
Duration: 11 Nov 202314 Nov 2023


  • Cross-domain learning
  • Graph Neural Networks
  • Protein-Protein Interactions
  • Unsupervised Domain Adaptation


Dive into the research topics of 'Cross-Domain Relation Adaptation'. Together they form a unique fingerprint.

Cite this