GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning.

Xin Dong|Ruize Wu|Chao Xiong|Hai Li|Lei Cheng|Yong He|Shiyou Qian|Jian Cao|Linjian Mo


Anthology ID:DBLP:conf/cikm/DongWXLCHQ0M22
Volume:Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA, October 17-21, 2022
Year:2022
Venue:International Conference on Information and Knowledge Management (CIKM)
Publisher:ACM
Pages:386-395
URL:https://doi.org/10.1145/3511808.3557333
DOI:https://doi.org/10.1145/3511808.3557333
DBLP:conf/cikm/DongWXLCHQ0M22
BibTeX:
@inproceedings{dong-2022-gdod, author = {Xin Dong and Ruize Wu and Chao Xiong and Hai Li and Lei Cheng and Yong He and Shiyou Qian and Jian Cao and Linjian Mo}, editor = {Mohammad Al Hasan and Li Xiong}, title = {{GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning}}, booktitle = {{Proceedings of the 31st ACM International Conference on Information & Knowledge Management, Atlanta, GA, USA, October 17-21, 2022}}, pages = {386--395}, publisher = {ACM}, year = {2022}, url = {https://doi.org/10.1145/3511808.3557333}, doi = {https://doi.org/10.1145/3511808.3557333} }