research
∙
08/16/2022
Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries
Knowledge graph (KG) embeddings have been a mainstream approach for reas...
share
research
∙
10/25/2021
NetMF+: Network Embedding Based on Fast and Effective Single-Pass Randomized Matrix Factorization
In this work, we propose NetMF+, a fast, memory-efficient, scalable, and...
research
∙
03/24/2021
FastMoE: A Fast Mixture-of-Expert Training System
Mixture-of-Expert (MoE) presents a strong potential in enlarging the siz...
research
∙
03/18/2021
All NLP Tasks Are Generation Tasks: A General Pretraining Framework
There have been various types of pretraining architectures including aut...
research
∙
11/07/2019
