Zhenyu Wang, Li Wan, Biqiao Zhang, Yiteng Huang, Shang-Wen Li, Ming Sun, Xin Lei, Zhaojun Yang
We propose data-source-aware disentangled learning with adversarial examples to reduce the mismatch between the original and adversarial data.
Areas
Research from Meta
All Publications
Raul Astudillo, Zhiyuan Jerry Lin, Eytan Bakshy, Peter I. Frazier
This work introduces the expected utility of the best option (qEUBO) as a novel acquisition function for PBO.
Umberto Minora, Martina Belmonte, Claudio Bosco, Drew Johnston, Eugenia Giraudy, Stefano M Iacus, Francesco Sermi
This work shows how innovative data from social media can provide useful insights on conflictinduced migration flows.
Areas
Susan B. Davidson, Shay Gershtein, Tova Milo, Slava Novgorodov, May Shoshan
We address this general problem in the context of image data (photos) by proposing which photos to archive to meet an online storage budget. The decision is based on factors such...
Areas
Xuhai Xu, Mengjie Yu, Tanya Jonker, Kashyap Todi, Feiyu Lu, Xun Qian, João Belo, Tianyi Wang, Michelle Li, Aran Mun, Te-Yen Wu, Junxiao Shen, Ting Zhang, Narine Kokhlikyan, Fulton Wang, Paul Sorenson, Sophie Kahyun Kim, Hrvoje Benko
We propose XAIR, a design framework that addresses when, what, and how to provide explanations of AI output in AR. The framework was based on a multi-disciplinary literature...
Wei Cai, Fuli Feng, Qifan Wang, Tian Yang, Zhenguang Liu, Congfu Xu
This work designs a method to estimate the item-level effects from the causal perspective. We resort to causal graphs to characterize the average treatment effect of...
Areas
Imanol Arrieta-Ibarra, Paman Gujral, Jonathan Tannen, Mark Tygert, Cherie Xu
The cumulative approach is currently unconventional, yet offers many favorable statistical properties, guaranteed via mathematical theory backed by rigorous proofs and...
Yifen Chen, Peter C. Rigby, Yulin Chen, Kun Jiang, Nader Dehghani, Qianying Huang, Peter Cottle, Clayton Andrews, Noah Lee, Nachi Nagappan
We describe descriptive statistics related to how long engineers are able to focus. We find that at Meta, Engineers have a total of 14.25 hours of personal-focus time per week.
Noah Lee, Rui Abreu, Nachi Nagappan
In this paper, we present our work on a code quality prediction framework, we call Automated Incremental Effort Investments (AIEI), to fasten the process of going from data...
Noah Lee, Rui Abreu, Mehmet Yatbaz, Hang Qu, Nachiappan Nagappan
In this paper, we present a real-world case study of an architectural refactoring project within an industrial setting. The system in scope is our codenamed ItemIndexer delivery...