1 code implementation • 2 Feb 2023 • Jianfei Gao, Yangze Zhou, Jincheng Zhou, Bruno Ribeiro
We then show how double-equivariant architectures are able to self-supervise pre-train on distinct KG domains and zero-shot predict links on a new KG domain (with completely new entities and new relation types).
1 code implementation • 5 Jul 2022 • Weihan Cao, Yifan Zhang, Jianfei Gao, Anda Cheng, Ke Cheng, Jian Cheng
First, the difference in feature magnitude between the teacher and the student could enforce overly strict constraints on the student.
1 code implementation • 12 Mar 2021 • Jianfei Gao, Bruno Ribeiro
This work formalizes the associational task of predicting node attribute evolution in temporal graphs from the perspective of learning equivariant representations.
3 code implementations • ICCV 2021 • Changyong Shu, Yifan Liu, Jianfei Gao, Zheng Yan, Chunhua Shen
Observing that in semantic segmentation, some layers' feature activations of each channel tend to encode saliency of scene categories (analogue to class activation mapping), we propose to align features channel-wise between the student and teacher networks.
no code implementations • 11 Feb 2020 • Jianfei Gao, Mohamed A. Zahran, Amit Sheoran, Sonia Fahmy, Bruno Ribeiro
We consider the task of learning a parametric Continuous Time Markov Chain (CTMC) sequence model without examples of sequences, where the training data consists entirely of aggregate steady-state statistics.