no code implementations • 24 May 2023 • Katherine Tian, Eric Mitchell, Allan Zhou, Archit Sharma, Rafael Rafailov, Huaxiu Yao, Chelsea Finn, Christopher D. Manning
A trustworthy real-world prediction system should be well-calibrated; that is, its confidence in an answer is indicative of the likelihood that the answer is correct, enabling deferral to a more expensive expert in cases of low-confidence predictions.
1 code implementation • 8 Apr 2023 • Yuzhen Mao, Zhun Deng, Huaxiu Yao, Ting Ye, Kenji Kawaguchi, James Zou
Although imposing fairness constraints have been studied extensively for classical machine learning models, the effect these techniques have on deep neural networks is still unclear.
no code implementations • 6 Feb 2023 • Huaxiu Yao, Xinyu Yang, Xinyi Pan, Shengchao Liu, Pang Wei Koh, Chelsea Finn
Distribution shift is a major challenge in machine learning, as models often perform poorly during the test stage if the test distribution differs from the training distribution.
1 code implementation • 25 Nov 2022 • Huaxiu Yao, Caroline Choi, Bochuan Cao, Yoonho Lee, Pang Wei Koh, Chelsea Finn
Temporal shifts -- distribution shifts arising from the passage of time -- often occur gradually and have the additional structure of timestamp metadata.
1 code implementation • 16 Nov 2022 • Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Cosgrove, Christopher D. Manning, Christopher Ré, Diana Acosta-Navas, Drew A. Hudson, Eric Zelikman, Esin Durmus, Faisal Ladhak, Frieda Rong, Hongyu Ren, Huaxiu Yao, Jue Wang, Keshav Santhanam, Laurel Orr, Lucia Zheng, Mert Yuksekgonul, Mirac Suzgun, Nathan Kim, Neel Guha, Niladri Chatterji, Omar Khattab, Peter Henderson, Qian Huang, Ryan Chi, Sang Michael Xie, Shibani Santurkar, Surya Ganguli, Tatsunori Hashimoto, Thomas Icard, Tianyi Zhang, Vishrav Chaudhary, William Wang, Xuechen Li, Yifan Mai, Yuhui Zhang, Yuta Koreeda
We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models.
no code implementations • 25 Oct 2022 • Xinyu Yang, Huaxiu Yao, Allan Zhou, Chelsea Finn
There is an inescapable long-tailed class-imbalance issue in many real-world classification problems.
no code implementations • 20 Oct 2022 • Yoonho Lee, Annie S. Chen, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, Chelsea Finn
A common approach to transfer learning under distribution shift is to fine-tune the last few layers of a pre-trained model, preserving learned features while also adapting to the new task.
1 code implementation • 11 Oct 2022 • Huaxiu Yao, Yiping Wang, Linjun Zhang, James Zou, Chelsea Finn
In this paper, we propose a simple yet powerful algorithm, C-Mixup, to improve generalization on regression tasks.
no code implementations • 11 Oct 2022 • Zhenbang Wu, Huaxiu Yao, Zhe Su, David M Liebovitz, Lucas M Glass, James Zou, Chelsea Finn, Jimeng Sun
However, newly approved drugs do not have much historical prescription data and cannot leverage existing drug recommendation methods.
1 code implementation • 27 May 2022 • Bin Lu, Xiaoying Gan, Weinan Zhang, Huaxiu Yao, Luoyi Fu, Xinbing Wang
To address this challenge, cross-city knowledge transfer has shown its promise, where the model learned from data-sufficient cities is leveraged to benefit the learning process of data-scarce cities.
no code implementations • ACL 2022 • Yingxiu Zhao, Zhiliang Tian, Huaxiu Yao, Yinhe Zheng, Dongkyu Lee, Yiping Song, Jian Sun, Nevin L. Zhang
Building models of natural language processing (NLP) is challenging in low-resource scenarios where only limited data are available.
1 code implementation • 7 Feb 2022 • Yoonho Lee, Huaxiu Yao, Chelsea Finn
Many datasets are underspecified: there exist multiple equally viable solutions to a given task.
2 code implementations • 2 Jan 2022 • Huaxiu Yao, Yu Wang, Sai Li, Linjun Zhang, Weixin Liang, James Zou, Chelsea Finn
Machine learning algorithms typically assume that training and test examples are drawn from the same distribution.
no code implementations • NeurIPS 2021 • Huaxiu Yao, Ying WEI, Long-Kai Huang, Ding Xue, Junzhou Huang, Zhenhui (Jessie) Li
More recently, there has been a surge of interest in employing machine learning approaches to expedite the drug discovery process where virtual screening for hit discovery and ADMET prediction for lead optimization play essential roles.
1 code implementation • NeurIPS 2021 • Huaxiu Yao, Yu Wang, Ying WEI, Peilin Zhao, Mehrdad Mahdavi, Defu Lian, Chelsea Finn
In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks.
1 code implementation • EMNLP 2021 • Huaxiu Yao, Yingxin Wu, Maruan Al-Shedivat, Eric P. Xing
Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task.
1 code implementation • ICLR 2022 • Huaxiu Yao, Linjun Zhang, Chelsea Finn
Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge.
no code implementations • ICLR Workshop Learning_to_Learn 2021 • Ali Ghadirzadeh, Petra Poklukar, Xi Chen, Huaxiu Yao, Hossein Azizpour, Mårten Björkman, Chelsea Finn, Danica Kragic
Few-shot meta-learning methods aim to learn the common structure shared across a set of tasks to facilitate learning new tasks with small amounts of data.
no code implementations • NeurIPS 2020 • Huaxiu Yao, Yingbo Zhou, Mehrdad Mahdavi, Zhenhui Li, Richard Socher, Caiming Xiong
When a new task is encountered, it constructs a meta-knowledge pathway by either utilizing the most relevant knowledge blocks or exploring new blocks.
no code implementations • 1 Aug 2020 • Jiatu Shi, Huaxiu Yao, Xian Wu, Tong Li, Zedong Lin, Tengfei Wang, Binqiang Zhao
The goal is to facilitate the learning process in the target segments by leveraging the learned knowledge from data-sufficient source segments.
1 code implementation • 26 Jul 2020 • Huaxiu Yao, Long-Kai Huang, Linjun Zhang, Ying WEI, Li Tian, James Zou, Junzhou Huang, Zhenhui Li
Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.
no code implementations • 28 Jun 2020 • Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Yiqi Wang, Jiliang Tang, Charu Aggarwal, Prasenjit Mitra, Suhang Wang
Pseudo labels increase the chance of connecting to labeled neighbors for low-degree nodes, thus reducing the biases of GCNs from the data perspective.
1 code implementation • ICLR 2020 • Huaxiu Yao, Xian Wu, Zhiqiang Tao, Yaliang Li, Bolin Ding, Ruirui Li, Zhenhui Li
In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones.
1 code implementation • 26 Nov 2019 • Chuxu Zhang, Huaxiu Yao, Chao Huang, Meng Jiang, Zhenhui Li, Nitesh V. Chawla
Knowledge graphs (KGs) serve as useful resources for various natural language processing applications.
no code implementations • 22 Nov 2019 • Xianfeng Tang, Huaxiu Yao, Yiwei Sun, Charu Aggarwal, Prasenjit Mitra, Suhang Wang
Thus, jointly modeling local and global temporal dynamics is very promising for MTS forecasting with missing values.
1 code implementation • 7 Oct 2019 • Huaxiu Yao, Chuxu Zhang, Ying WEI, Meng Jiang, Suhang Wang, Junzhou Huang, Nitesh V. Chawla, Zhenhui Li
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
no code implementations • 7 Sep 2019 • Ying Wei, Peilin Zhao, Huaxiu Yao, Junzhou Huang
Automated machine learning aims to automate the whole process of machine learning, including model configuration.
no code implementations • 29 Aug 2019 • Guanjie Zheng, Mengqi Liu, Tao Wen, Hongjian Wang, Huaxiu Yao, Susan L. Brantley, Zhenhui Li
In the face of growing needs for water and energy, a fundamental understanding of the environmental impacts of human activities becomes critical for managing water and energy resources, remedying water pollution, and making regulatory policy wisely.
1 code implementation • 20 Aug 2019 • Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, Suhang Wang
To optimize PA-GNN for a poisoned graph, we design a meta-optimization algorithm that trains PA-GNN to penalize perturbations using clean graphs and their adversarial counterparts, and transfers such ability to improve the robustness of PA-GNN on the poisoned graph.
Ranked #23 on Node Classification on Pubmed
1 code implementation • 13 May 2019 • Huaxiu Yao, Ying WEI, Junzhou Huang, Zhenhui Li
In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks.
no code implementations • 25 Feb 2019 • Xianfeng Tang, Boqing Gong, Yanwei Yu, Huaxiu Yao, Yandong Li, Haiyong Xie, Xiaoyu Wang
In this paper, we propose a novel framework for the citywide traffic volume inference using both dense GPS trajectories and incomplete trajectories captured by camera surveillance systems.
1 code implementation • 24 Jan 2019 • Huaxiu Yao, Yiding Liu, Ying WEI, Xianfeng Tang, Zhenhui Li
Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm.
5 code implementations • 3 Mar 2018 • Huaxiu Yao, Xianfeng Tang, Hua Wei, Guanjie Zheng, Zhenhui Li
Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i. e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical.
1 code implementation • 23 Feb 2018 • Huaxiu Yao, Fei Wu, Jintao Ke, Xianfeng Tang, Yitian Jia, Siyu Lu, Pinghua Gong, Jieping Ye, Zhenhui Li
Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations.