1.2k citations · 9.1k across the 205 of their papers we have counts for
36 papers · 1 filter
Cooperative Policy Learning with Pre-trained Heterogeneous Observation Representations
Wenlei Shi, Xinran Wei, Jia Zhang +4
Multi-agent reinforcement learning (MARL) has been increasingly explored to learn the cooperative policy towards maximizing a certain global reward. Many existing studies take adva…
DenoiSpeech: Denoising Text to Speech with Frame-Level Noise Modeling
Chen Zhang, Yi Ren, Xu Tan +5
While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many sce…
Latent Causal Invariant Model
Xinwei Sun, Botong Wu, Xiangyu Zheng +4
Current supervised learning can learn spurious correlation during the data-fitting process, imposing issues regarding interpretability, out-of-distribution (OOD) generalization, an…
Learning Causal Semantic Representation for Out-of-Distribution Prediction
Chang Liu, Xinwei Sun, Jindong Wang +5
Conventional supervised learning methods, especially deep ones, are found to be sensitive to out-of-distribution (OOD) examples, largely because the learned representation mixes th…
COSEA: Convolutional Code Search with Layer-wise Attention
Hao Wang, Jia Zhang, Yingce Xia +3
Semantic code search, which aims to retrieve code snippets relevant to a given natural language query, has attracted many research efforts with the purpose of accelerating software…
Qlib: An AI-oriented Quantitative Investment Platform
Xiao Yang, Weiqing Liu, Dong Zhou +2
Quantitative investment aims to maximize the return and minimize the risk in a sequential trading period over a set of financial instruments. Recently, inspired by rapid developmen…
DualLip: A System for Joint Lip Reading and Generation
Weicong Chen, Xu Tan, Yingce Xia +3
Lip reading aims to recognize text from talking lip, while lip generation aims to synthesize talking lip according to text, which is a key component in talking face generation and…
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis
Jiawei Chen, Xu Tan, Jian Luan +2
High-fidelity singing voices usually require higher sampling rate (e.g., 48kHz) to convey expression and emotion. However, higher sampling rate causes the wider frequency band and…
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
Tianle Cai, Shengjie Luo, Keyulu Xu +3
Normalization is known to help the optimization of deep neural networks. Curiously, different architectures require specialized normalization methods. In this paper, we study what…
PopMAG: Pop Music Accompaniment Generation
Yi Ren, Jinzheng He, Xu Tan +3
In pop music, accompaniments are usually played by multiple instruments (tracks) such as drum, bass, string and guitar, and can make a song more expressive and contagious by arrang…
Variance-reduced Language Pretraining via a Mask Proposal Network
Liang Chen
Self-supervised learning, a.k.a., pretraining, is important in natural language processing. Most of the pretraining methods first randomly mask some positions in a sentence and the…
LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition
Jin Xu, Xu Tan, Yi Ren +4
Speech synthesis (text to speech, TTS) and recognition (automatic speech recognition, ASR) are important speech tasks, and require a large amount of text and speech pairs for model…
Taking Notes on the Fly Helps BERT Pre-training
Qiyu Wu, Chen Xing, Yatao Li +3
How to make unsupervised language pre-training more efficient and less resource-intensive is an important research direction in NLP. In this paper, we focus on improving the effici…
Learning to Match Distributions for Domain Adaptation
Chaohui Yu, Jindong Wang, Chang Liu +5
When the training and test data are from different distributions, domain adaptation is needed to reduce dataset bias to improve the model's generalization ability. Since it is diff…
Multi-branch Attentive Transformer
Yang Fan, Shufang Xie, Yingce Xia +4
While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especia…
DeepSinger: Singing Voice Synthesis with Data Mined From the Web
Yi Ren, Xu Tan, Tao Qin +3
In this paper, we develop DeepSinger, a multi-lingual multi-singer singing voice synthesis (SVS) system, which is built from scratch using singing training data mined from music we…
Modeling Lost Information in Lossy Image Compression
Yaolong Wang, Mingqing Xiao, Chang Liu +2
Lossy image compression is one of the most commonly used operators for digital images. Most recently proposed deep-learning-based image compression methods leverage the auto-encode…
How Does Data Augmentation Affect Privacy in Machine Learning?
Da Yu, Huishuai Zhang, Wei Chen +2
It is observed in the literature that data augmentation can significantly mitigate membership inference (MI) attack. However, in this work, we challenge this observation by proposi…
Temporally Correlated Task Scheduling for Sequence Learning
Xueqing Wu, Lewen Wang, Yingce Xia +5
Sequence learning has attracted much research attention from the machine learning community in recent years. In many applications, a sequence learning task is usually associated wi…
Accuracy Prediction with Non-neural Model for Neural Architecture Search
Renqian Luo, Xu Tan, Rui Wang +3
Neural architecture search (NAS) with an accuracy predictor that predicts the accuracy of candidate architectures has drawn increasing attention due to its simplicity and effective…
Learning to Reweight with Deep Interactions
Yang Fan, Yingce Xia, Lijun Wu +5
Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real t…
SEEK: Segmented Embedding of Knowledge Graphs
Wentao Xu, Shun Zheng, Liang He +3
In recent years, knowledge graph embedding becomes a pretty hot research topic of artificial intelligence and plays increasingly vital roles in various downstream applications, suc…
MC-BERT: Efficient Language Pre-Training via a Meta Controller
Zhenhui Xu, Linyuan Gong, Guolin Ke +5
Pre-trained contextual representations (e.g., BERT) have become the foundation to achieve state-of-the-art results on many NLP tasks. However, large-scale pre-training is computati…
Rethinking Positional Encoding in Language Pre-training
Guolin Ke, Di He, Tie-Yan Liu
In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show t…