Differentiable Graph Optimization for Neural Architecture Search

no code implementations • 1 Jan 2021 • Chengyue Huang, Lingfei Wu, Yadong Ding, Siliang Tang, Fangli Xu, Chang Zong, Chilie Tan, Yueting Zhuang

To this end, we learn a differentiable graph neural network as a surrogate model to rank candidate architectures, which enable us to obtain gradient w. r. t the input architectures.

Bayesian Optimization Neural Architecture Search

Robust Meta-learning with Noise via Eigen-Reptile

no code implementations • 1 Jan 2021 • Dong Chen, Lingfei Wu, Siliang Tang, Fangli Xu, Juncheng Li, Chang Zong, Chilie Tan, Yueting Zhuang

In particular, we first cast the meta-overfitting problem (overfitting on sampling and label noise) as a gradient noise problem since few available samples cause meta-learner to overfit on existing examples (clean or corrupted) of an individual task at every gradient step.

Few-Shot Learning

DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization

no code implementations • IJCNLP 2019 • Chujie Lu, Long Chen, Chilie Tan, Xiaolin Li, Jun Xiao

In this paper, we focus on natural language video localization: localizing (ie, grounding) a natural language description in a long and untrimmed video sequence.