Timezone: »
Multi-Task Learning (MTL) is a powerful learning paradigm to improve generalization performance via knowledge sharing. However, existing studies find that MTL could sometimes hurt generalization, especially when two tasks are less correlated. One possible reason that hurts generalization is spurious correlation, i.e., some knowledge is spurious and not causally related to task labels, but the model could mistakenly utilize them and thus fail when such correlation changes. In MTL setup, there exist several unique challenges of spurious correlation. First, the risk of having non-causal knowledge is higher, as the shared MTL model needs to encode all knowledge from different tasks, and causal knowledge for one task could be potentially spurious to the other. Second, the confounder between task labels brings in a different type of spurious correlation to MTL. Given such label-label confounders, we theoretically and empirically show that MTL is prone to taking non-causal knowledge from other tasks. To solve this problem, we propose Multi-Task Causal Representation Learning (MT-CRL) framework. MT-CRL aims to represent multi-task knowledge via disentangled neural modules, and learn which module is causally related to each task via MTL-specific invariant regularization. Experiments show that MT-CRL could enhance MTL model's performance by 5.5% on average over Multi-MNIST, MovieLens, Taskonomy, CityScape, and NYUv2, and show it could indeed alleviate spurious correlation problem.
Author Information
Ziniu Hu (UCLA)
Zhe Zhao (Google)
Xinyang Yi (Google)
Tiansheng Yao (University of California, Los Angeles)
Lichan Hong (Google Research)
Yizhou Sun (UCLA)
Ed Chi (Google Inc.)
d H. Chi is a Principal Scientist at Google, leading several machine learning research teams focusing on neural modeling, inclusive ML, reinforcement learning, and recommendation systems in Google Brain team. He has delivered significant improvements for YouTube, News, Ads, Google Play Store at Google with >325 product launches in the last 6 years. With 39 patents and over 120 research articles, he is also known for research on user behavior in web and social media. Prior to Google, he was the Area Manager and a Principal Scientist at Palo Alto Research Center's Augmented Social Cognition Group, where he led the team in understanding how social systems help groups of people to remember, think and reason. Ed completed his three degrees (B.S., M.S., and Ph.D.) in 6.5 years from University of Minnesota. Recognized as an ACM Distinguished Scientist and elected into the CHI Academy, he recently received a 20-year Test of Time award for research in information visualization. He has been featured and quoted in the press, including the Economist, Time Magazine, LA Times, and the Associated Press. An avid swimmer, photographer and snowboarder in his spare time, he also has a blackbelt in Taekwondo.
More from the Same Authors
-
2021 Spotlight: Efficiently Identifying Task Groupings for Multi-Task Learning »
Chris Fifty · Ehsan Amid · Zhe Zhao · Tianhe Yu · Rohan Anil · Chelsea Finn -
2022 Poster: Transformer Memory as a Differentiable Search Index »
Yi Tay · Vinh Tran · Mostafa Dehghani · Jianmo Ni · Dara Bahri · Harsh Mehta · Zhen Qin · Kai Hui · Zhe Zhao · Jai Gupta · Tal Schuster · William Cohen · Donald Metzler -
2022 : Towards Companion Recommendation Systems »
Konstantina Christakopoulou · Yuyan Wang · Ed Chi · MINMIN CHEN -
2022 : Group Excess Risk Bound of Overparameterized Linear Regression with Constant-Stepsize SGD »
Arjun Subramonian · Levent Sagun · Kai-Wei Chang · Yizhou Sun -
2022 : Unit Selection: Learning Benefit Function from Finite Population Data »
Ang Li · Song Jiang · Yizhou Sun · Judea Pearl -
2022 : Dissimilar Nodes Improve Graph Active Learning »
Zhicheng Ren · Yifu Yuan · Yuxin Wu · Xiaxuan Gao · Yewen Wang · Yizhou Sun -
2022 : Empowering Language Models with Knowledge Graph Reasoning for Question Answering »
Ziniu Hu · Yichong Xu · Wenhao Yu · Shuohang Wang · Ziyi Yang · Chenguang Zhu · Kai-Wei Chang · Yizhou Sun -
2022 Spotlight: Improving Multi-Task Generalization via Regularizing Spurious Correlation »
Ziniu Hu · Zhe Zhao · Xinyang Yi · Tiansheng Yao · Lichan Hong · Yizhou Sun · Ed Chi -
2022 Workshop: New Frontiers in Graph Learning »
Jiaxuan You · Marinka Zitnik · Rex Ying · Yizhou Sun · Hanjun Dai · Stefanie Jegelka -
2022 Poster: Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks »
Minji Yoon · John Palowitch · Dustin Zelle · Ziniu Hu · Ruslan Salakhutdinov · Bryan Perozzi -
2022 Poster: On the Discrimination Risk of Mean Aggregation Feature Imputation in Graphs »
Arjun Subramonian · Kai-Wei Chang · Yizhou Sun -
2022 Poster: GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games »
Shichang Zhang · Yozen Liu · Neil Shah · Yizhou Sun -
2022 Poster: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models »
Jason Wei · Xuezhi Wang · Dale Schuurmans · Maarten Bosma · brian ichter · Fei Xia · Ed Chi · Quoc V Le · Denny Zhou -
2021 Poster: DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning »
Hussein Hazimeh · Zhe Zhao · Aakanksha Chowdhery · Maheswaran Sathiamoorthy · Yihua Chen · Rahul Mazumder · Lichan Hong · Ed Chi -
2021 Poster: Efficiently Identifying Task Groupings for Multi-Task Learning »
Chris Fifty · Ehsan Amid · Zhe Zhao · Tianhe Yu · Rohan Anil · Chelsea Finn -
2021 Poster: Improving Calibration through the Relationship with Adversarial Robustness »
Yao Qin · Xuezhi Wang · Alex Beutel · Ed Chi -
2020 : Invited Speaker: Ed Chi »
Ed Chi -
2020 Poster: Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations »
Zijie Huang · Yizhou Sun · Wei Wang -
2020 Poster: Fairness without Demographics through Adversarially Reweighted Learning »
Preethi Lahoti · Alex Beutel · Jilin Chen · Kang Lee · Flavien Prost · Nithum Thain · Xuezhi Wang · Ed Chi -
2019 Workshop: Graph Representation Learning »
Will Hamilton · Rianne van den Berg · Michael Bronstein · Stefanie Jegelka · Thomas Kipf · Jure Leskovec · Renjie Liao · Yizhou Sun · Petar Veličković -
2019 Poster: Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks »
Difan Zou · Ziniu Hu · Yewen Wang · Song Jiang · Yizhou Sun · Quanquan Gu -
2018 : Poster Session (All Posters) »
Stephen Macke · Hongzi Mao · Caroline Lemieux · Saim Salman · Rishikesh Jha · Hanrui Wang · Shoumik P Palkar · Tianqi Chen · Thomas Pumir · Vaishnav Janardhan · adit bhardwaj · Ed Chi -
2017 : Ed Chi (Google) on Learned Deep Retrieval for Recommenders »
Ed Chi