Publications

Light Multi-segment Activation for Model Compression

Published in In Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Propose a more powerful activation for improving the performance of compressed student model under teacher-student compression framework.

Recommended citation: Zhenhui Xu, Guolin Ke, Jia Zhang, Jiang Bian, and Tie-Yan Liu. "Light Multi-segment Activation for Model Compression." In Thirty-Fourth AAAI Conference on Artificial Intelligence, AAAI, 2020.

DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks

Published in In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019

Combine the advantages of NN and GBDT for tabular data under a knowledge distillation framework.

Recommended citation: Guolin Ke, Zhenhui Xu, Jia Zhang, Jiang Bian, and Tie-Yan Liu. "DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks." In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, 2019.