no code implementations • 7 May 2024 • Yijiang Pang, Shuyang Yu, Bao Hoang, Jiayu Zhou
To tackle this challenge, in this paper, we propose a novel parameter-free optimizer, AdamG (Adam with the golden step size), designed to automatically adapt to diverse optimization problems without manual tuning.
no code implementations • 23 Apr 2024 • Ali Abbasi, Fan Dong, Xin Wang, Henry Leung, Jiayu Zhou, Steve Drew
Federated learning (FL) provides a promising collaborative framework to build a model from distributed clients, and this work investigates the carbon emission of the FL process.
no code implementations • 11 Mar 2024 • Yuyang Deng, Junyuan Hong, Jiayu Zhou, Mehrdad Mahdavi
Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization.
no code implementations • 2 Feb 2024 • Yijiang Pang, Jiayu Zhou
The theoretical properties also shed light on a faster and more stable S2P variant, Accelerated S2P (AS2P), through exploiting our new convergence properties that better represent the dynamics of deep models in training.
no code implementations • 2 Feb 2024 • Yijiang Pang, Bao Hoang, Jiayu Zhou
Specifically, in the context of the distributional robustness of CLIP, we propose to leverage natural language inputs to debias the image feature representations, to improve worst-case performance on sub-populations.
no code implementations • 19 Dec 2023 • Xiaodan Zhang, Sandeep Vemulapalli, Nabasmita Talukdar, Sumyeong Ahn, Jiankun Wang, Han Meng, Sardar Mehtab Bin Murtaza, Aakash Ajay Dave, Dmitry Leshchiner, Dimitri F. Joseph, Martin Witteveen-Lane, Dave Chesla, Jiayu Zhou, Bin Chen
This study assesses the ability of state-of-the-art large language models (LLMs) including GPT-3. 5, GPT-4, Falcon, and LLaMA 2 to identify patients with mild cognitive impairment (MCI) from discharge summaries and examines instances where the models' responses were misaligned with their reasoning.
no code implementations • 8 Dec 2023 • Xuan Wang, Guanhong Wang, Wenhao Chai, Jiayu Zhou, Gaoang Wang
Moreover, we employ GPT-2 as the frozen large language model.
1 code implementation • NeurIPS 2023 • Haobo Zhang, Junyuan Hong, Yuyang Deng, Mehrdad Mahdavi, Jiayu Zhou
Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors.
1 code implementation • 4 Sep 2023 • Shuyang Yu, Junyuan Hong, Haobo Zhang, Haotao Wang, Zhangyang Wang, Jiayu Zhou
Training a high-performance deep neural network requires large amounts of data and computational resources.
1 code implementation • 20 Jun 2023 • Siqi Liang, Jintao Huang, Junyuan Hong, Dun Zeng, Jiayu Zhou, Zenglin Xu
Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients.
1 code implementation • 4 Jun 2023 • Junyuan Hong, Yi Zeng, Shuyang Yu, Lingjuan Lyu, Ruoxi Jia, Jiayu Zhou
Data-free knowledge distillation (KD) helps transfer knowledge from a pre-trained model (known as the teacher model) to a smaller model (known as the student model) without access to the original training data used for training the teacher model.
Backdoor Defense for Data-Free Distillation with Poisoned Teachers Data-free Knowledge Distillation
no code implementations • 24 May 2023 • Fan Dong, Ali Abbasi, Henry Leung, Xin Wang, Jiayu Zhou, Steve Drew
Direct sharing of the data distribution may be prohibitive due to the additional private information that is sent from the clients.
no code implementations • 10 May 2023 • Suraj Rajendran, Weishen Pan, Mert R. Sabuncu, Yong Chen, Jiayu Zhou, Fei Wang
By offering a more comprehensive approach to healthcare data integration, patchwork learning has the potential to revolutionize the clinical applicability of ML models.
1 code implementation • 18 Mar 2023 • Jingyi Hou, Zhen Dong, Jiayu Zhou, Zhijie Liu
Many real-world data mining tasks, however, lack sufficient variables for relation reasoning, and therefore these methods may not properly handle such forecasting problems.
no code implementations • 15 Mar 2023 • Qianqian Xie, Jiayu Zhou, Yifan Peng, Fei Wang
We propose to extract medical facts of the input medical report, its gold summary, and candidate summaries based on the RadGraph schema and design the fact-guided reranker to efficiently incorporate the extracted medical facts for selecting the optimal summary.
no code implementations • 14 Feb 2023 • Jiajun Wu, Steve Drew, Jiayu Zhou
One major challenge preventing the wide adoption of FL in IoT is the pervasive power supply constraints of IoT devices due to the intensive energy consumption of battery-powered clients for local training and model updates.
1 code implementation • 7 Feb 2023 • Haobo Zhang, Junyuan Hong, Fan Dong, Steve Drew, Liangjie Xue, Jiayu Zhou
Developing a mechanism for battling financial crimes is an impending task that requires in-depth collaboration from multiple institutions, and yet such collaboration imposed significant technical challenges due to the privacy and security requirements of distributed financial data.
no code implementations • 6 Feb 2023 • Jiajun Wu, Steve Drew, Fan Dong, Zhuangdi Zhu, Jiayu Zhou
The ultra-low latency requirements of 5G/6G applications and privacy constraints call for distributed machine learning systems to be deployed at the edge.
1 code implementation • ICLR 2023 • Shuyang Yu, Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
We propose to take advantage of such heterogeneity and turn the curse into a blessing that facilitates OoD detection in FL.
2 code implementations • ICLR 2023 • Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger
The proposed MECTA is efficient and can be seamlessly plugged into state-of-theart CTA algorithms at negligible overhead on computation and memory.
no code implementations • 23 Oct 2022 • Junyuan Hong, Lingjuan Lyu, Jiayu Zhou, Michael Spranger
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device.
1 code implementation • 12 Oct 2022 • Haotao Wang, Junyuan Hong, Aston Zhang, Jiayu Zhou, Zhangyang Wang
As a result, both the stem and the classification head in the final network are hardly affected by backdoor training samples.
no code implementations • 11 Jul 2022 • Yijiang Pang, Boyang Liu, Jiayu Zhou
In this paper, we show a surprising fact that contrastive pre-training has an interesting yet implicit connection with robustness, and such natural robustness in the pre trained representation enables us to design a powerful robust algorithm against adversarial attacks, RUSH, that combines the standard contrastive pre-training and randomized smoothing.
no code implementations • 4 Jul 2022 • Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang
Increasing concerns have been raised on deep learning fairness in recent years.
1 code implementation • ICLR 2022 • Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
In this paper, we propose a novel Split-Mix FL strategy for heterogeneous participants that, once training is done, provides in-situ customization of model sizes and robustness.
1 code implementation • AAAI 2022 • Mengying Sun, Fei Wang, Olivier Elemento, Jiayu Zhou
In this work, we proposed a DDI detection method based on molecular structures using graph convolutional networks and deep sets.
2 code implementations • 25 Oct 2021 • Fengyi Tang, Lifan Zeng, Fei Wang, Jiayu Zhou
In this paper we define and investigate the problem of \emph{persona authentication}: learning a conversational policy to verify the consistency of persona models.
no code implementations • 29 Sep 2021 • Haotao Wang, Junyuan Hong, Jiayu Zhou, Zhangyang Wang
In this paper, we first propose a new fairness goal, termed Equalized Robustness (ER), to impose fair model robustness against unseen distribution shifts across majority and minority groups.
no code implementations • 29 Sep 2021 • Boyang Liu, Zhuangdi Zhu, Pang-Ning Tan, Jiayu Zhou
We first discuss the limitations of directly using the noisy-label defense algorithms to defend against backdoor attacks.
1 code implementation • the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining 2021 • Junyuan Hong, Zhuangdi Zhu, Shuyang Yu, Zhangyang Wang, Hiroko Dodge, Jiayu Zhou
While adversarial learning is commonly used in centralized learning for mitigating bias, there are significant barriers when extending it to the federated framework.
1 code implementation • 18 Jun 2021 • Junyuan Hong, Haotao Wang, Zhangyang Wang, Jiayu Zhou
In this paper, we study a novel FL strategy: propagating adversarial robustness from rich-resource users that can afford AT, to those with poor resources that cannot afford it, during federated learning.
1 code implementation • 5 Jun 2021 • Mengying Sun, Jing Xing, Huijun Wang, Bin Chen, Jiayu Zhou
Second, the contrastive scheme only learns representations that are invariant to local perturbations and thus does not consider the global structure of the dataset, which may also be useful for downstream tasks.
4 code implementations • 20 May 2021 • Zhuangdi Zhu, Junyuan Hong, Jiayu Zhou
Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data.
no code implementations • 10 May 2021 • Haomin Yu, Yangli-ao Geng, Yingjun Zhang, Qingyong Li, Jiayu Zhou
Despite the popularity of this single-task schema, it may neglect interactions among calibration tasks of different sensors, which encompass underlying information to promote calibration performance.
no code implementations • 7 Apr 2021 • Divyansh Aggarwal, Jiayu Zhou, Anil K. Jain
DNN-based face recognition models require large centrally aggregated face datasets for training.
1 code implementation • 15 Mar 2021 • Zhizhe Liu, Zhenfeng Zhu, Shuai Zheng, Yang Liu, Jiayu Zhou, Yao Zhao
To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning.
1 code implementation • NeurIPS 2020 • Zhuangdi Zhu, Kaixiang Lin, Bo Dai, Jiayu Zhou
To further accelerate the learning procedure, we regulate the policy update with an inverse action model, which assists distribution matching from the perspective of mode-covering.
no code implementations • 12 Feb 2021 • Boyang Liu, Mengying Sun, Ding Wang, Pang-Ning Tan, Jiayu Zhou
Training deep neural models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact the generalization performance.
no code implementations • 19 Jan 2021 • Junyuan Hong, Zhangyang Wang, Jiayu Zhou
In this paper, we provide comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions.
no code implementations • 1 Jan 2021 • Junyuan Hong, Zhangyang Wang, Jiayu Zhou
In this paper, we provide comprehensive analysis of noise influence in dynamic privacy schedules to answer these critical questions.
2 code implementations • 1 Jan 2021 • Boyang Liu, Ding Wang, Kaixiang Lin, Pang-Ning Tan, Jiayu Zhou
Unsupervised anomaly detection plays a crucial role in many critical applications.
no code implementations • 1 Jan 2021 • Boyang Liu, Mengying Sun, Ding Wang, Pang-Ning Tan, Jiayu Zhou
Training deep neural models in the presence of corrupted supervisions is challenging as the corrupted data points may significantly impact the generalization performance.
no code implementations • 26 Dec 2020 • Mengying Sun, Jing Xing, Bin Chen, Jiayu Zhou
In this paper, we study the underlying mechanism of how disagreement and agreement between networks can help reduce the noise in gradients and develop a novel framework called Robust Collaborative Learning (RCL) that leverages both disagreement and agreement among networks.
no code implementations • 16 Sep 2020 • Zhuangdi Zhu, Kaixiang Lin, Anil K. Jain, Jiayu Zhou
Reinforcement learning is a learning paradigm for solving sequential decision-making problems.
no code implementations • 11 Jul 2020 • Zhaonan Qu, Kaixiang Lin, Zhaojian Li, Jiayu Zhou, Zhengyuan Zhou
For strongly convex and convex problems, we also characterize the corresponding convergence rates for the Nesterov accelerated FedAvg algorithm, which are the first linear speedup guarantees for momentum variants of FedAvg in convex settings.
1 code implementation • 1 Apr 2020 • Zhuangdi Zhu, Kaixiang Lin, Bo Dai, Jiayu Zhou
SAIL bridges the advantages of IL and RL to reduce the sample complexity substantially, by effectively exploiting sup-optimal demonstrations and efficiently exploring the environment to surpass the demonstrated performance.
1 code implementation • ICLR 2020 • Kaixiang Lin, Jiayu Zhou
Sample inefficiency is a long-lasting problem in reinforcement learning (RL).
1 code implementation • 8 May 2019 • Xi Sheryl Zhang, Fengyi Tang, Hiroko Dodge, Jiayu Zhou, Fei Wang
In this paper, we propose MetaPred, a meta-learning for clinical risk prediction from longitudinal patient EHRs.
no code implementations • 1 May 2019 • Yongshun Gong, Jin-Feng Yi, Dong-Dong Chen, Jian Zhang, Jiayu Zhou, Zhihua Zhou
In this paper, we aim to infer the significance of every item's appearance in consumer decision making and identify the group of items that are suitable for screenless shopping.
no code implementations • 22 Apr 2019 • Mohit Sharma, Jiayu Zhou, Junling Hu, George Karypis
The user personalized non-collaborative methods based on item features can be used to address this item cold-start problem.
2 code implementations • NeurIPS 2018 • Lifang He, Kun Chen, Wanwan Xu, Jiayu Zhou, Fei Wang
We propose a sparse and low-rank tensor regression model to relate a univariate outcome to a feature tensor, in which each unit-rank tensor from the CP decomposition of the coefficient tensor is assumed to be sparse.
1 code implementation • 18 Sep 2018 • Jian Liang, Ziqi Liu, Jiayu Zhou, Xiaoqian Jiang, Chang-Shui Zhang, Fei Wang
Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together.
1 code implementation • 22 May 2018 • Xi Sheryl Zhang, Lifang He, Kun Chen, Yuan Luo, Jiayu Zhou, Fei Wang
Parkinson's Disease (PD) is one of the most prevalent neurodegenerative diseases that affects tens of millions of Americans.
1 code implementation • 28 Apr 2018 • Tengfei Ma, Cao Xiao, Jiayu Zhou, Fei Wang
In this paper, we propose to learn accurate and interpretable similarity measures from multiple types of drug features.
no code implementations • 15 Mar 2018 • Jiayu Zhou, Fengyi Tang, He Zhu, Ning Nan, Ziheng Zhou
However, one key challenge in distributed data vending is the trade-off dilemma between the effectiveness of data retrieval, and the leakage risk from indexing the data.
1 code implementation • ICLR 2018 • Mengying Sun, Inci M. Baytas, Liang Zhan, Zhangyang Wang, Jiayu Zhou
Over the past decade a wide spectrum of machine learning models have been developed to model the neurodegenerative diseases, associating biomarkers, especially non-intrusive neuroimaging markers, with key clinical scores measuring the cognitive status of patients.
2 code implementations • 19 Feb 2018 • Liyang Xie, Kaixiang Lin, Shu Wang, Fei Wang, Jiayu Zhou
Generative Adversarial Network (GAN) and its variants have recently attracted intensive research interests due to their elegant theoretical foundation and excellent empirical performance as generative models.
no code implementations • 18 Feb 2018 • Fengyi Tang, Kaixiang Lin, Ikechukwu Uchendu, Hiroko H. Dodge, Jiayu Zhou
Even though there is mild cognitive decline in MCI patients, they have normal overall cognition and thus is challenging to distinguish from normal aging.
1 code implementation • 18 Feb 2018 • Kaixiang Lin, Renyu Zhao, Zhe Xu, Jiayu Zhou
Large-scale online ride-sharing platforms have substantially transformed our lives by reallocating transportation resources to alleviate traffic congestion and promote transportation efficiency.
no code implementations • 13 Feb 2018 • Mengying Sun, Fengyi Tang, Jin-Feng Yi, Fei Wang, Jiayu Zhou
The surging availability of electronic medical records (EHR) leads to increased research interests in medical predictive modeling.
no code implementations • 16 Nov 2017 • Dan Ma, Bin Liu, Zhao Kang, Jiayu Zhou, Jianke Zhu, Zenglin Xu
Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications.
1 code implementation • KDD '17 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 2017 • Inci M. Baytas, Cao Xiao, Xi Zhang, Fei Wang, Anil K. Jain, Jiayu Zhou
We propose a patient subtyping model that leverages the proposed T-LSTM in an auto-encoder to learn a powerful single representation for sequential records of patients, which are then used to cluster patients into clinical subtypes.
Ranked #4 on Multivariate Time Series Forecasting on USHCN-Daily
no code implementations • CVPR 2017 • Luan Tran, Xiaoming Liu, Jiayu Zhou, Rong Jin
To leverage the valuable information in the corrupted data, we propose to impute the missing data by leveraging the relatedness among different modalities.
1 code implementation • 19 Feb 2017 • Kaixiang Lin, Shu Wang, Jiayu Zhou
Motivated by human collaborative learning, in this paper we propose a collaborative deep reinforcement learning (CDRL) framework that performs adaptive knowledge transfer among heterogeneous learning agents.
1 code implementation • 30 Sep 2016 • Inci M. Baytas, Ming Yan, Anil K. Jain, Jiayu Zhou
The models for each hospital may be different because of the inherent differences in the distributions of the patient populations.
no code implementations • 1 Sep 2015 • Zhangyang Wang, Shiyu Chang, Jiayu Zhou, Meng Wang, Thomas S. Huang
In this paper, we propose to emulate the sparse coding-based clustering pipeline in the context of deep learning, leading to a carefully crafted deep model benefiting from both.
no code implementations • NeurIPS 2014 • Jie Wang, Jiayu Zhou, Jun Liu, Peter Wonka, Jieping Ye
The l1-regularized logistic regression (or sparse logistic regression) is a widely used method for simultaneous classification and feature selection.
no code implementations • NeurIPS 2011 • Jiayu Zhou, Jianhui Chen, Jieping Ye
We further establish the equivalence relationship between the proposed convex relaxation of CMTL and an existing convex relaxation of ASO, and show that the proposed convex CMTL formulation is significantly more efficient especially for high-dimensional data.