no code implementations • EACL (BEA) 2021 • Haoran Zhang, Diane Litman
However, because AES typically uses supervised machine learning, a human-graded essay corpus is still required to train the AES model.
1 code implementation • 23 Feb 2023 • Yuzhe Yang, Haoran Zhang, Dina Katabi, Marzyeh Ghassemi
Machine learning models often perform poorly on subgroups that are underrepresented in the training data.
no code implementations • 2 Feb 2023 • Jiaxiang Dong, Haixu Wu, Haoran Zhang, Li Zhang, Jianmin Wang, Mingsheng Long
By relating masked modeling to manifold learning, SimMTM proposes to recover masked time points by the weighted aggregation of multiple neighbors outside the manifold, which eases the reconstruction task by assembling ruined but complementary temporal variations from multiple masked series.
no code implementations • 15 Nov 2022 • Haoran Zhang, Junhui Wang
Longitudinal network consists of a sequence of temporal edges among multiple nodes, where the temporal edges are observed in real time.
no code implementations • 19 Oct 2022 • Haoran Zhang, Harvineet Singh, Marzyeh Ghassemi, Shalmali Joshi
In this work, we introduce the problem of attributing performance differences between environments to distribution shifts in the underlying data generating mechanisms.
no code implementations • 8 Jul 2022 • Haoran Zhang, Junhui Wang
This paper develops a unified embedding model for signed networks to disentangle the intertwined balance structure and anomaly effect, which can greatly facilitate the downstream analysis, including community detection, anomaly detection, and network inference.
no code implementations • 6 May 2022 • Aparna Balagopalan, Haoran Zhang, Kimia Hamidieh, Thomas Hartvigsen, Frank Rudzicz, Marzyeh Ghassemi
Across two different blackbox model architectures and four popular explainability methods, we find that the approximation quality of explanation models, also known as the fidelity, differs significantly between subgroups.
no code implementations • 4 Apr 2022 • Zifeng Zhao, Dongchao Yang, Rongzhi Gu, Haoran Zhang, Yuexian Zou
However, its performance is often inferior to that of a blind source separation (BSS) counterpart with a similar network architecture, due to the auxiliary speaker encoder may sometimes generate ambiguous speaker embeddings.
1 code implementation • 23 Mar 2022 • Haoran Zhang, Natalie Dullerud, Karsten Roth, Lauren Oakden-Rayner, Stephen Robert Pfohl, Marzyeh Ghassemi
We also find that methods which achieve group fairness do so by worsening performance for all groups.
no code implementations • 23 Feb 2022 • Haoran Zhang, Chenkun Yin, Yanxin Zhang, Shangtai Jin, Zhenxuan Li
A new expert data generation method, called Model Predictive Based Expert (MPBE) which combines Model Predictive Control and Deep Deterministic Policy Gradient, is developed to provide high quality supervision data for RLfD algorithms.
1 code implementation • NeurIPS 2021 • Haoran Zhang, Quaid Morris, Berk Ustun, Marzyeh Ghassemi
Our results show that our method can fit simple predictive checklists that perform well and that can easily be customized to obey a rich class of custom constraints.
no code implementations • 21 Nov 2021 • Dou Huang, Haoran Zhang, Xuan Song, Ryosuke Shibasaki
In this paper, we propose to use a differentiable projection layer in DNN instead of directly solving time-consuming KKT conditions.
1 code implementation • 28 Oct 2021 • Jinhui Yuan, Xinqi Li, Cheng Cheng, Juncheng Liu, Ran Guo, Shenghang Cai, Chi Yao, Fei Yang, Xiaodong Yi, Chuan Wu, Haoran Zhang, Jie Zhao
Aiming at a simple, neat redesign of distributed deep learning frameworks for various parallelism paradigms, we present OneFlow, a novel distributed training framework based on an SBP (split, broadcast and partial-value) abstraction and the actor model.
no code implementations • 17 Sep 2021 • Jinyu Chen, Haoran Zhang, Xuan Song, Ryosuke Shibasaki
In this study, we propose and open GPS trajectory dataset marked with travel mode and benchmark for the travel mode detection.
1 code implementation • 27 Aug 2021 • Sindhu C. M. Gowda, Shalmali Joshi, Haoran Zhang, Marzyeh Ghassemi
This systematic investigation underlines the importance of accounting for the underlying data-generating mechanisms and fortifying data-preprocessing pipelines with a causal framework to develop methods robust to confounding biases.
1 code implementation • 27 Aug 2021 • Stephen R. Pfohl, Haoran Zhang, Yizhe Xu, Agata Foryciarz, Marzyeh Ghassemi, Nigam H. Shah
Predictive models for clinical outcomes that are accurate on average in a patient population may underperform drastically for some subpopulations, potentially introducing or reinforcing inequities in care access and quality.
no code implementations • 25 Jul 2021 • Chandrajit Bajaj, Avik Roy, Haoran Zhang
Variational Autoencoders (VAEs) have been shown to be remarkably effective in recovering model latent spaces for several computer vision tasks.
no code implementations • 21 Jul 2021 • Imon Banerjee, Ananth Reddy Bhimireddy, John L. Burns, Leo Anthony Celi, Li-Ching Chen, Ramon Correa, Natalie Dullerud, Marzyeh Ghassemi, Shih-Cheng Huang, Po-Chih Kuo, Matthew P Lungren, Lyle Palmer, Brandon J Price, Saptarshi Purkayastha, Ayis Pyrros, Luke Oakden-Rayner, Chima Okechukwu, Laleh Seyyed-Kalantari, Hari Trivedi, Ryan Wang, Zachary Zaiman, Haoran Zhang, Judy W Gichoya
Methods: Using private and public datasets we evaluate: A) performance quantification of deep learning models to detect race from medical images, including the ability of these models to generalize to external environments and across multiple imaging modalities, B) assessment of possible confounding anatomic and phenotype population features, such as disease distribution and body habitus as predictors of race, and C) investigation into the underlying mechanism by which AI models can recognize race.
1 code implementation • 20 Mar 2021 • Haoran Zhang, Natalie Dullerud, Laleh Seyyed-Kalantari, Quaid Morris, Shalmali Joshi, Marzyeh Ghassemi
In this work, we benchmark the performance of eight domain generalization methods on multi-site clinical time series and medical imaging data.
1 code implementation • 11 Dec 2020 • Yuntian Chen, Dou Huang, Dongxiao Zhang, Junsheng Zeng, Nanzhe Wang, Haoran Zhang, Jinyue Yan
Machine learning models have been successfully used in many scientific and engineering fields.
no code implementations • COLING 2020 • Na Liu, Xiangdong Su, Haoran Zhang, Guanglai Gao, Feilong Bao
The inner-word encoder uses the self-attention mechanisms to capture the inner-word features of the target word.
1 code implementation • 23 Nov 2020 • Taylor W. Killian, Haoran Zhang, Jayakumar Subramanian, Mehdi Fatemi, Marzyeh Ghassemi
Reinforcement Learning (RL) has recently been applied to sequential estimation and prediction problems identifying and developing hypothetical treatment strategies for septic patients, with a particular focus on offline learning with observational data.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Yuekai Zhao, Haoran Zhang, Shuchang Zhou, Zhihua Zhang
Active learning is an efficient approach for mitigating data dependency when training neural machine translation (NMT) models.
no code implementations • ACL 2020 • Haoran Zhang, Diane Litman
While automated essay scoring (AES) can reliably grade essays at scale, automated writing evaluation (AWE) additionally provides formative feedback to guide essay revision.
no code implementations • NAACL 2021 • Qingyun Wang, Manling Li, Xuan Wang, Nikolaus Parulian, Guangxing Han, Jiawei Ma, Jingxuan Tu, Ying Lin, Haoran Zhang, Weili Liu, Aabhas Chauhan, Yingjun Guan, Bangzheng Li, Ruisong Li, Xiangchen Song, Yi R. Fung, Heng Ji, Jiawei Han, Shih-Fu Chang, James Pustejovsky, Jasmine Rah, David Liem, Ahmed Elsayed, Martha Palmer, Clare Voss, Cynthia Schneider, Boyan Onyshkevych
To combat COVID-19, both clinicians and scientists need to digest vast amounts of relevant biomedical knowledge in scientific literature to understand the disease mechanism and related biological functions.
1 code implementation • 11 Mar 2020 • Haoran Zhang, Amy X. Lu, Mohamed Abdalla, Matthew McDermott, Marzyeh Ghassemi
In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks.
no code implementations • ACL 2017 • Haoran Zhang, Diane Litman
Our long-term goal is to also use this scoring method to provide formative feedback to students and teachers about students' writing quality.
1 code implementation • WS 2018 • Haoran Zhang, Diane Litman
This paper presents an investigation of using a co-attention based neural network for source-dependent essay scoring.
no code implementations • 6 Aug 2019 • Haoran Zhang, Ahmed Magooda, Diane Litman, Richard Correnti, Elaine Wang, Lindsay Clare Matsumura, Emily Howe, Rafael Quintana
Writing a good essay typically involves students revising an initial paper draft after receiving feedback.
1 code implementation • 13 Dec 2018 • Wesley Tansey, Kathy Li, Haoran Zhang, Scott W. Linderman, Raul Rabadan, David M. Blei, Chris H. Wiggins
Personalized cancer treatments based on the molecular profile of a patient's tumor are an emerging and exciting class of treatments in oncology.
3 code implementations • 1 Nov 2018 • Wesley Tansey, Victor Veitch, Haoran Zhang, Raul Rabadan, David M. Blei
We propose the holdout randomization test (HRT), an approach to feature selection using black box predictive models.