1 code implementation • 18 Jul 2022 • Chonghan Chen, Haohan Wang, Leyang Hu, Yuhao Zhang, Shuguang Lyu, Jingcheng Wu, Xinnuo Li, Linjing Sun, Eric P. Xing
We introduce the initial release of our software Robustar, which aims to improve the robustness of vision classification machine learning models through a data-driven perspective.
no code implementations • 18 Jul 2022 • Yifan Zhong, Haohan Wang, Eric P. Xing
Many recent neural models have shown remarkable empirical results in Machine Reading Comprehension, but evidence suggests sometimes the models take advantage of dataset biases to predict and fail to generalize on out-of-sample data.
no code implementations • 26 Jun 2022 • Peiyan Zhang, Jiayan Guo, Chaozhuo Li, Yueqi Xie, Jaeboum Kim, Yan Zhang, Xing Xie, Haohan Wang, Sunghun Kim
Based on this observation, we intuitively propose to remove the GNN propagation part, while the readout module will take on more responsibility in the model reasoning process.
no code implementations • 18 Jun 2022 • Chonghan Chen, Qi Jiang, Chih-Hao Wang, Noel Chen, Haohan Wang, Xiang Li, Bhiksha Raj
With our proposed QCM, the downstream fusion module receives visual features that are more discriminative and focused on the desired object described in the expression, leading to more accurate predictions.
1 code implementation • 4 Jun 2022 • Haohan Wang, Zeyi Huang, Xindi Wu, Eric P. Xing
Finally, we test this simple technique we identify (worst-case data augmentation with squared l2 norm alignment regularization) and show that the benefits of this method outrun those of the specially designed methods.
1 code implementation • 9 Apr 2022 • Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee, Eric P. Xing
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.
no code implementations • CVPR 2022 • Zeyi Huang, Haohan Wang, Dong Huang, Yong Jae Lee, Eric P. Xing
Training with an emphasis on "hard-to-learn" components of the data has been proven as an effective method to improve the generalization of machine learning models, especially in the settings where robustness (e. g., generalization across distributions) is valued.
no code implementations • NAACL 2022 • Xuezhi Wang, Haohan Wang, Diyi Yang
Despite robustness being an increasingly studied topic, it has been separately explored in applications like vision and NLP, with various definitions, evaluation and mitigation strategies in multiple lines of research.
1 code implementation • 5 Nov 2021 • Haohan Wang, Zeyi Huang, HANLIN ZHANG, Yong Jae Lee, Eric Xing
Machine learning has demonstrated remarkable prediction accuracy over i. i. d data, but the accuracy often drops when tested with data from another distribution.
no code implementations • 5 Nov 2021 • Haohan Wang, Bryon Aragam, Eric Xing
Motivated by empirical arguments that are well-known from the genome-wide association studies (GWAS) literature, we study the statistical properties of linear mixed models (LMMs) applied to GWAS.
1 code implementation • NeurIPS 2021 • Songwei Ge, Shlok Mishra, Haohan Wang, Chun-Liang Li, David Jacobs
We also show that model bias favors texture and shape features differently under different test settings.
no code implementations • 24 Feb 2021 • Zhuoling Li, Haohan Wang, Tymoteusz Swistek, Weixin Chen, Yuanzheng Li, Haoqian Wang
Few-shot learning is challenging due to the limited data and labels.
no code implementations • 24 Feb 2021 • Xuefeng Du, Haohan Wang, Zhenxi Zhu, Xiangrui Zeng, Yi-Wei Chang, Jing Zhang, Min Xu
Deep learning based subtomogram classification have played critical roles for such tasks.
no code implementations • 1 Jan 2021 • Haohan Wang, Zeyi Huang, Xindi Wu, Eric Xing
Data augmentation is one of the most popular techniques for improving the robustness of neural networks.
no code implementations • 1 Jan 2021 • Haohan Wang, Zeyi Huang, Eric Xing
In this paper, we formally study the generalization error bound for this setup with the knowledge of how the spurious features are associated with the label.
1 code implementation • 25 Nov 2020 • Haohan Wang, Zeyi Huang, Xindi Wu, Eric P. Xing
Data augmentation is one of the most popular techniques for improving the robustness of neural networks.
no code implementations • 20 Oct 2020 • Haohan Wang, Peiyan Zhang, Eric P. Xing
Neural machine translation has achieved remarkable empirical performance over standard benchmark datasets, yet recent evidence suggests that the models can still fail easily dealing with substandard inputs such as misspelled words, To overcome this issue, we introduce a new encoding heuristic of the input symbols for character-level NLP models: it encodes the shape of each character through the images depicting the letters when printed.
7 code implementations • ECCV 2020 • Zeyi Huang, Haohan Wang, Eric P. Xing, Dong Huang
We introduce a simple training heuristic, Representation Self-Challenging (RSC), that significantly improves the generalization of CNN to the out-of-domain data.
Ranked #12 on
Domain Generalization
on PACS
1 code implementation • CVPR 2020 • Haohan Wang, Xindi Wu, Zeyi Huang, Eric P. Xing
We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN).
no code implementations • ICLR 2020 • Haohan Wang, Xindi Wu, Songwei Ge, Zachary C. Lipton, Eric P. Xing
Recent research has shown that CNNs are often overly sensitive to high-frequency textural patterns.
1 code implementation • WS 2019 • He He, Sheng Zha, Haohan Wang
We first learn a biased model that only uses features that are known to relate to dataset bias.
4 code implementations • NeurIPS 2019 • Haohan Wang, Songwei Ge, Eric P. Xing, Zachary C. Lipton
Despite their renowned predictive power on i. i. d.
Ranked #79 on
Domain Generalization
on PACS
1 code implementation • 28 May 2019 • Haohan Wang, Xindi Wu, Zeyi Huang, Eric P. Xing
We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN).
no code implementations • ICLR 2019 • Haohan Wang, Zexue He, Zachary C. Lipton, Eric P. Xing
We test our method on the battery of standard domain generalization data sets and, interestingly, achieve comparable or better performance as compared to other domain generalization methods that explicitly require samples from the target distribution for training.
Ranked #88 on
Domain Generalization
on PACS
no code implementations • 7 Sep 2018 • Haohan Wang, Da Sun, Eric P. Xing
In this paper, we further investigate the statistical irregularities, what we refer as confounding factors, of the NLI data sets.
1 code implementation • 20 Mar 2018 • Haohan Wang, Zhenglin Wu, Eric P. Xing
The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis.
no code implementations • 2 Feb 2018 • Tianwei Yue, Haohan Wang
Advancements in genomic research such as high-throughput sequencing techniques have driven modern genomic studies into "big data" disciplines.
no code implementations • 11 Nov 2017 • Wenting Ye, Xiang Liu, Haohan Wang, Eric P. Xing
We proposed the sparse graph-structured linear mixed model (sGLMM) that can incorporate the relatedness information from traits in a dataset with confounding correction.
no code implementations • 24 Feb 2017 • Haohan Wang, Bhiksha Raj
This paper is a review of the evolutionary history of deep learning models.
no code implementations • 29 Nov 2016 • Jingkang Yang, Haohan Wang, Jun Zhu, Eric P. Xing
In this paper, we propose an extension of State Space Model to work with different sources of information together with its learning and inference algorithms.
1 code implementation • 16 Sep 2016 • Haohan Wang, Aaksha Meghawat, Louis-Philippe Morency, Eric P. Xing
In this paper, we propose a Select-Additive Learning (SAL) procedure that improves the generalizability of trained neural networks for multimodal sentiment analysis.
no code implementations • 6 Nov 2015 • Haohan Wang, Madhavi K. Ganapathiraju
In order for the predicted interactions to be directly adopted by biologists, the ma- chine learning predictions have to be of high precision, regardless of recall.
no code implementations • 16 Oct 2015 • Haohan Wang, Bhiksha Raj
Further, we will also look into the development history of modelling time series data with neural networks.
no code implementations • 18 Sep 2015 • Haohan Wang, Madhavi K. Ganapathiraju
In this paper, we focused on the problem that non-availability of accurately labeled testing data sets in the domain of protein-protein interaction (PPI) prediction may lead to biased evaluation results.
no code implementations • 9 Dec 2014 • Seungwhan Moon, Suyoun Kim, Haohan Wang
We propose a transfer deep learning (TDL) framework that can transfer the knowledge obtained from a single-modal neural network to a network with a different modality.
no code implementations • 9 Jul 2014 • Ming Xu, Jianping Wu, Yiman Du, Haohan Wang, Geqi Qi, Kezhen Hu, Yun-Peng Xiao
However, none of existing approaches addresses the problem of identifying network-wide important crossroads in real road network.