359 citations · 1k across the 68 of their papers we have counts for
29 papers · 1 filter
Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability
Haoyi Xiong, Xuhong Li, Boyang Yu +3
Random label noises (or observational noises) widely exist in practical machine learning settings. While previous studies primarily focus on the affects of label noises to the perf…
Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution
Yan Li, Xinjiang Lu, Haoyi Xiong +4
Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high…
Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios
Xueying Zhan, Zeyu Dai, Qingzhong Wang +4
Pool-based Active Learning (AL) has achieved great success in minimizing labeling cost by sequentially selecting informative unlabeled samples from a large unlabeled data pool and…
A Comparative Survey of Deep Active Learning
Xueying Zhan, Qingzhong Wang, Kuan-hao Huang +3
While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small p…
SenseMag: Enabling Low-Cost Traffic Monitoring using Non-invasive Magnetic Sensing
Kafeng Wang, Haoyi Xiong, Jie Zhang +3
The operation and management of intelligent transportation systems (ITS), such as traffic monitoring, relies on real-time data aggregation of vehicular traffic information, includi…
AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow
Haiyan Jiang, Haoyi Xiong, Dongrui Wu +2
Principal component analysis (PCA) has been widely used as an effective technique for feature extraction and dimension reduction. In the High Dimension Low Sample Size (HDLSS) sett…
Exploring the Common Principal Subspace of Deep Features in Neural Networks
Haoran Liu, Haoyi Xiong, Yaqing Wang +3
We find that different Deep Neural Networks (DNNs) trained with the same dataset share a common principal subspace in latent spaces, no matter in which architectures (e.g., Convolu…
Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study
Xuhong Li, Haoyi Xiong, Siyu Huang +2
Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for…
AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Yihang Yin, Qingzhong Wang, Siyu Huang +2
Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the…
Robust Matrix Factorization with Grouping Effect
Haiyan Jiang, Shuyu Li, Luwei Zhang +2
Although many techniques have been applied to matrix factorization (MF), they may not fully exploit the feature structure. In this paper, we incorporate the grouping effect into MF…
From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques
Zhiyuan Wang, Haoyi Xiong, Jie Zhang +5
Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote h…
Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Xuanyu Wu, Xuhong Li, Haoyi Xiong +3
Training images with data transformations have been suggested as contrastive examples to complement the testing set for generalization performance evaluation of deep neural network…
Optimization Variance: Exploring Generalization Properties of DNNs
Xiao Zhang, Dongrui Wu, Haoyi Xiong +1
Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, i…
SMILE: Self-Distilled MIxup for Efficient Transfer LEarning
Xingjian Li, Haoyi Xiong, Chengzhong Xu +1
To improve the performance of deep learning, mixup has been proposed to force the neural networks favoring simple linear behaviors in-between training samples. Performing mixup for…
Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond
Xuhong Li, Haoyi Xiong, Xingjian Li +5
Deep neural networks have been well-known for their superb handling of various machine learning and artificial intelligence tasks. However, due to their over-parameterized black-bo…
C-Watcher: A Framework for Early Detection of High-Risk Neighborhoods Ahead of COVID-19 Outbreak
Congxi Xiao, Jingbo Zhou, Jizhou Huang +4
The novel coronavirus disease (COVID-19) has crushed daily routines and is still rampaging through the world. Existing solution for nonpharmaceutical interventions usually needs to…
Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement
Xingjian Li, Di Hu, Xuhong Li +5
Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples. To obtain b…
XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
Xingjian Li, Haoyi Xiong, Haozhe An +2
Transferring knowledge from large source datasets is an effective way to fine-tune the deep neural networks of the target task with a small sample size. A great number of algorithm…
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
Xingjian Li, Haoyi Xiong, Haozhe An +2
Fine-tuning the deep convolution neural network(CNN) using a pre-trained model helps transfer knowledge learned from larger datasets to the target task. While the accuracy could be…
COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization
Xingjian Li, Haoyi Xiong, Haozhe An +2
Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs). While such a practice ha…
Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
Xiao Zhang, Haoyi Xiong, Dongrui Wu
Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance tra…
SecureGBM: Secure Multi-Party Gradient Boosting
Zhi Fengy, Haoyi Xiong, Chuanyuan Song +7
Federated machine learning systems have been widely used to facilitate the joint data analytics across the distributed datasets owned by the different parties that do not trust eac…
Towards Making Deep Transfer Learning Never Hurt
Ruosi Wan, Haoyi Xiong, Xingjian Li +2
Transfer learning have been frequently used to improve deep neural network training through incorporating weights of pre-trained networks as the starting-point of optimization for…
On the Noisy Gradient Descent that Generalizes as SGD
Jingfeng Wu, Wenqing Hu, Haoyi Xiong +3
The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning. While past studies confirm that the magnitude and t…