Can graph neural networks learn structural roles? Stay tuned for our full paper “Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework“, accepted at #ICDM2020. Joint work with Junting wang, @AditKrishnan, and Hari Sundaram. Preprint coming soon!
Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation
https://t.co/nKM0JYQynJ
by Adit Krishnan et al. including @MahashwetaDas#ComputerScience#Learning