145 citations · 424 across the 41 of their papers we have counts for
42 papers
Supported Trust Region Optimization for Offline Reinforcement Learning
Yixiu Mao, Hongchang Zhang, Chen Chen +2
Offline reinforcement learning suffers from the out-of-distribution issue and extrapolation error. Most policy constraint methods regularize the density of the trained policy towar…
Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model
Mingxin Li, Richong Zhang, Zhijie Nie +1
Sentence Representation Learning (SRL) is a fundamental task in Natural Language Processing (NLP), with the Contrastive Learning of Sentence Embeddings (CSE) being the mainstream t…
3D ScatterNet: Inference from 21 cm Light-cones
Xiaosheng Zhao, Shifan Zuo, Yi Mao
The Square Kilometre Array (SKA) will have the sensitivity to take the 3D light-cones of the 21 cm signal from the epoch of reionization. This signal, however, is highly non-Gaussi…
Evaluating Summary Statistics with Mutual Information for Cosmological Inference
Ce Sui, Xiaosheng Zhao, Tao Jing +1
The ability to compress observational data and accurately estimate physical parameters relies heavily on informative summary statistics. In this paper, we introduce the use of mutu…
Multi-fidelity Emulator for Cosmological Large Scale 21 cm Lightcone Images: a Few-shot Transfer Learning Approach with GAN
Kangning Diao, Yi Mao
Large-scale numerical simulations () of cosmic reionization are required to match the large survey volume of the upcoming Square Kilometre Array (SKA). We pres…
Can Diffusion Model Conditionally Generate Astrophysical Images?
Xiaosheng Zhao, Yuan-Sen Ting, Kangning Diao +1
Generative adversarial networks (GANs) are frequently utilized in astronomy to construct an emulator of numerical simulations. Nevertheless, training GANs can prove to be a precari…
ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification
Junfan Chen, Richong Zhang, Yongyi Mao +1
Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets…
Adversarial Defenses via Vector Quantization
Zhiyi Dong, Yongyi Mao
Adversarial attacks pose significant challenges to the robustness of modern deep neural networks in computer vision, and defending these networks against adversarial attacks has at…
Adversarial Word Dilution as Text Data Augmentation in Low-Resource Regime
Junfan Chen, Richong Zhang, Zheyan Luo +2
Data augmentation is widely used in text classification, especially in the low-resource regime where a few examples for each class are available during training. Despite the succes…
Self-training through Classifier Disagreement for Cross-Domain Opinion Target Extraction
Kai Sun, Richong Zhang, Samuel Mensah +3
Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining that aims to extract the targets (or aspects) on which opinions have been expresse…
Tighter Information-Theoretic Generalization Bounds from Supersamples
Ziqiao Wang, Yongyi Mao
In this work, we present a variety of novel information-theoretic generalization bounds for learning algorithms, from the supersample setting of Steinke & Zakynthinou (2020)-the se…
Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States
Ziqiao Wang, Yongyi Mao
Stochastic differential equations (SDEs) have been shown recently to characterize well the dynamics of training machine learning models with SGD. When the generalization error of t…
Information-Theoretic Analysis of Unsupervised Domain Adaptation
Ziqiao Wang, Yongyi Mao
This paper uses information-theoretic tools to analyze the generalization error in unsupervised domain adaptation (UDA). We present novel upper bounds for two notions of generaliza…
A Semi-blind PCA-based Foreground Subtraction Method for 21 cm Intensity Mapping
Shifan Zuo, Xuelei Chen, Yi Mao
The Principal Component Analysis (PCA) method and the Singular Value Decomposition (SVD) method are widely used for foreground subtraction in 21 cm intensity mapping experiments. W…
Cross Domain Few-Shot Learning via Meta Adversarial Training
Jirui Qi, Richong Zhang, Chune Li +1
Few-shot relation classification (RC) is one of the critical problems in machine learning. Current research merely focuses on the set-ups that both training and testing are from th…
Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation
Qianben Chen, Richong Zhang, Yaowei Zheng +1
Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to…
ifMixup: Interpolating Graph Pair to Regularize Graph Classification
Hongyu Guo, Yongyi Mao
We present a simple and yet effective interpolation-based regularization technique, aiming to improve the generalization of Graph Neural Networks (GNNs) on supervised graph classif…
On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications
Ziqiao Wang, Yongyi Mao
This paper follows up on a recent work of Neu et al. (2021) and presents some new information-theoretic upper bounds for the generalization error of machine learning models, such a…
Robust Regularization with Adversarial Labelling of Perturbed Samples
Xiaohui Guo, Richong Zhang, Yaowei Zheng +1
Recent researches have suggested that the predictive accuracy of neural network may contend with its adversarial robustness. This presents challenges in designing effective regular…
A Hypergradient Approach to Robust Regression without Correspondence
Yujia Xie, Yixiu Mao, Simiao Zuo +4
We consider a variant of regression problem, where the correspondence between input and output data is not available. Such shuffled data is commonly observed in many real world pro…
On the Dynamics of Training Attention Models
Haoye Lu, Yongyi Mao, Amiya Nayak
The attention mechanism has been widely used in deep neural networks as a model component. By now, it has become a critical building block in many state-of-the-art natural language…
Parallel Interactive Networks for Multi-Domain Dialogue State Generation
Junfan Chen, Richong Zhang, Yongyi Mao +1
The dependencies between system and user utterances in the same turn and across different turns are not fully considered in existing multidomain dialogue state tracking (MDST) mode…
Neural Dialogue State Tracking with Temporally Expressive Networks
Junfan Chen, Richong Zhang, Yongyi Mao +1
Dialogue state tracking (DST) is an important part of a spoken dialogue system. Existing DST models either ignore temporal feature dependencies across dialogue turns or fail to exp…
Regularizing Neural Networks via Adversarial Model Perturbation
Yaowei Zheng, Richong Zhang, Yongyi Mao
Effective regularization techniques are highly desired in deep learning for alleviating overfitting and improving generalization. This work proposes a new regularization scheme, ba…