Tie-Yan Liu

is this you? claim profile

∙ 0 followers
Microsoft

Principal Research Manager at Microsoft Research Asia

Large Scale Private Learning via Low-rank Reparametrization

We propose a reparametrization scheme to address the challenges of apply...
06/17/2021 ∙ by Da Yu, et al. ∙ 0 ∙ share

read it
Dual-view Molecule Pre-training

Inspired by its success in natural language processing and computer visi...
06/17/2021 ∙ by Jinhua Zhu, et al. ∙ 0 ∙ share

read it
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior

Denoising diffusion probabilistic models have been recently proposed to ...
06/11/2021 ∙ by Sang-gil Lee, et al. ∙ 5 ∙ share

read it
Do Transformers Really Perform Bad for Graph Representation?

The Transformer architecture has become a dominant choice in many domain...
06/09/2021 ∙ by Chengxuan Ying, et al. ∙ 16 ∙ share

read it
Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics

Learning dynamics governed by differential equations is crucial for pred...
06/08/2021 ∙ by Shiqi Gong, et al. ∙ 0 ∙ share

read it
Machine-Learning Non-Conservative Dynamics for New-Physics Detection

Energy conservation is a basic physics principle, the breakdown of which...
05/31/2021 ∙ by Ziming Liu, et al. ∙ 0 ∙ share

read it
Adversarial Training with Rectified Rejection

Adversarial training (AT) is one of the most effective strategies for pr...
05/31/2021 ∙ by Tianyu Pang, et al. ∙ 0 ∙ share

read it
NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search

While pre-trained language models (e.g., BERT) have achieved impressive ...
05/30/2021 ∙ by Jin Xu, et al. ∙ 12 ∙ share

read it
Learning Structures for Deep Neural Networks

In this paper, we focus on the unsupervised setting for structure learni...
05/27/2021 ∙ by Jinhui Yuan, et al. ∙ 0 ∙ share

read it
How could Neural Networks understand Programs?

Semantic understanding of programs is a fundamental problem for programm...
05/10/2021 ∙ by Dinglan Peng, et al. ∙ 0 ∙ share

read it
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition

Error correction techniques have been used to refine the output sentence...
05/09/2021 ∙ by Yichong Leng, et al. ∙ 5 ∙ share

read it
AdaSpeech 2: Adaptive Text to Speech with Untranscribed Data

Text to speech (TTS) is widely used to synthesize personal voice for a t...
04/20/2021 ∙ by Yuzi Yan, et al. ∙ 13 ∙ share

read it
UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost

Transformer architecture achieves great success in abundant natural lang...
04/11/2021 ∙ by Zhen Wu, et al. ∙ 0 ∙ share

read it
IOT: Instance-wise Layer Reordering for Transformer Structures

With sequentially stacked self-attention, (optional) encoder-decoder att...
03/05/2021 ∙ by Jinhua Zhu, et al. ∙ 0 ∙ share

read it
AdaSpeech: Adaptive Text to Speech for Custom Voice

Custom voice, a specific text to speech (TTS) service in commercial spee...
03/01/2021 ∙ by Mingjian Chen, et al. ∙ 25 ∙ share

read it
LazyFormer: Self Attention with Lazy Update

Improving the efficiency of Transformer-based language pre-training is a...
02/25/2021 ∙ by Chengxuan Ying, et al. ∙ 0 ∙ share

read it
Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning

The privacy leakage of the model about the training data can be bounded ...
02/25/2021 ∙ by Da Yu, et al. ∙ 0 ∙ share

read it
Return-Based Contrastive Representation Learning for Reinforcement Learning

Recently, various auxiliary tasks have been proposed to accelerate repre...
02/22/2021 ∙ by Guoqing Liu, et al. ∙ 0 ∙ share

read it
Revisiting Language Encoding in Learning Multilingual Representations

Transformer has demonstrated its great power to learn contextual word re...
02/16/2021 ∙ by Shengjie Luo, et al. ∙ 0 ∙ share

read it
REST: Relational Event-driven Stock Trend Forecasting

Stock trend forecasting, aiming at predicting the stock future trends, i...
02/15/2021 ∙ by Wentao Xu, et al. ∙ 0 ∙ share

read it
LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search

Text to speech (TTS) has been broadly used to synthesize natural and int...
02/08/2021 ∙ by Renqian Luo, et al. ∙ 14 ∙ share

read it
BN-invariant sharpness regularizes the training model to better generalization

It is arguably believed that flatter minima can generalize better. Howev...
01/08/2021 ∙ by Mingyang Yi, et al. ∙ 0 ∙ share

read it
Cooperative Policy Learning with Pre-trained Heterogeneous Observation Representations

Multi-agent reinforcement learning (MARL) has been increasingly explored...
12/24/2020 ∙ by Wenlei Shi, et al. ∙ 0 ∙ share

read it
DenoiSpeech: Denoising Text to Speech with Frame-Level Noise Modeling

While neural-based text to speech (TTS) models can synthesize natural an...
12/17/2020 ∙ by Chen Zhang, et al. ∙ 0 ∙ share

read it
Latent Causal Invariant Model

Current supervised learning can learn spurious correlation during the da...
11/04/2020 ∙ by Xinwei Sun, et al. ∙ 0 ∙ share

read it
Learning Causal Semantic Representation for Out-of-Distribution Prediction

Conventional supervised learning methods, especially deep ones, are foun...
11/03/2020 ∙ by Chang Liu, et al. ∙ 1 ∙ share

read it
COSEA: Convolutional Code Search with Layer-wise Attention

Semantic code search, which aims to retrieve code snippets relevant to a...
10/19/2020 ∙ by Hao Wang, et al. ∙ 16 ∙ share

read it
Qlib: An AI-oriented Quantitative Investment Platform

Quantitative investment aims to maximize the return and minimize the ris...
09/22/2020 ∙ by Xiao Yang, et al. ∙ 0 ∙ share

read it
DualLip: A System for Joint Lip Reading and Generation

Lip reading aims to recognize text from talking lip, while lip generatio...
09/12/2020 ∙ by Weicong Chen, et al. ∙ 0 ∙ share

read it
GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

Normalization plays an important role in the optimization of deep neural...
09/07/2020 ∙ by Tianle Cai, et al. ∙ 1 ∙ share

read it
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis

High-fidelity singing voices usually require higher sampling rate (e.g.,...
09/03/2020 ∙ by Jiawei Chen, et al. ∙ 0 ∙ share

read it
PopMAG: Pop Music Accompaniment Generation

In pop music, accompaniments are usually played by multiple instruments ...
08/18/2020 ∙ by Yi Ren, et al. ∙ 0 ∙ share

read it
LRSpeech: Extremely Low-Resource Speech Synthesis and Recognition

Speech synthesis (text to speech, TTS) and recognition (automatic speech...
08/09/2020 ∙ by Jin Xu, et al. ∙ 0 ∙ share

read it
Taking Notes on the Fly Helps BERT Pre-training

How to make unsupervised language pre-training more efficient and less r...
08/04/2020 ∙ by Qiyu Wu, et al. ∙ 0 ∙ share

read it
Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary

Membership inference (MI) in machine learning decides whether a given ex...
07/21/2020 ∙ by Da Yu, et al. ∙ 11 ∙ share

read it
Task-Level Curriculum Learning for Non-Autoregressive Neural Machine Translation

Non-autoregressive translation (NAT) achieves faster inference speed but...
07/17/2020 ∙ by Jinglin Liu, et al. ∙ 0 ∙ share

read it
Learning to Match Distributions for Domain Adaptation

When the training and test data are from different distributions, domain...
07/17/2020 ∙ by Chaohui Yu, et al. ∙ 11 ∙ share

read it
Learn to Use Future Information in Simultaneous Translation

Simultaneous neural machine translation (briefly, NMT) has attracted muc...
07/10/2020 ∙ by Xueqing Wu, et al. ∙ 0 ∙ share

read it
Neural Architecture Search with GBDT

Neural architecture search (NAS) with an accuracy predictor that predict...
07/09/2020 ∙ by Renqian Luo, et al. ∙ 5 ∙ share

read it
Learning to Teach with Deep Interactions

Machine teaching uses a meta/teacher model to guide the training of a st...
07/09/2020 ∙ by Yang Fan, et al. ∙ 0 ∙ share

read it
DeepSinger: Singing Voice Synthesis with Data Mined From the Web

In this paper, we develop DeepSinger, a multi-lingual multi-singer singi...
07/09/2020 ∙ by Yi Ren, et al. ∙ 0 ∙ share

read it
Rethinking Positional Encoding in Language Pre-training

How to explicitly encode positional information into neural networks is ...
06/28/2020 ∙ by Guolin Ke, et al. ∙ 0 ∙ share

read it
Rethinking the Positional Encoding in Language Pre-training

How to explicitly encode positional information into neural networks is ...
06/28/2020 ∙ by Guolin Ke, et al. ∙ 0 ∙ share

read it
Dynamic of Stochastic Gradient Descent with State-Dependent Noise

Stochastic gradient descent (SGD) and its variants are mainstream method...
06/24/2020 ∙ by Qi Meng, et al. ∙ 10 ∙ share

read it
Modeling Lost Information in Lossy Image Compression

Lossy image compression is one of the most commonly used operators for d...
06/22/2020 ∙ by Yaolong Wang, et al. ∙ 8 ∙ share

read it
Multi-branch Attentive Transformer

While the multi-branch architecture is one of the key ingredients to the...
06/18/2020 ∙ by Yang Fan, et al. ∙ 0 ∙ share

read it
UWSpeech: Speech to Speech Translation for Unwritten Languages

Existing speech to speech translation systems heavily rely on the text o...
06/14/2020 ∙ by Chen Zhang, et al. ∙ 0 ∙ share

read it
MC-BERT: Efficient Language Pre-Training via a Meta Controller

Pre-trained contextual representations (e.g., BERT) have become the foun...
06/10/2020 ∙ by Zhenhui Xu, et al. ∙ 0 ∙ share

read it
MultiSpeech: Multi-Speaker Text to Speech with Transformer

Transformer-based text to speech (TTS) model (e.g., Transformer TTS <cit...
06/08/2020 ∙ by Mingjian Chen, et al. ∙ 0 ∙ share

read it
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

Advanced text to speech (TTS) models such as FastSpeech can synthesize s...
06/08/2020 ∙ by Yi Ren, et al. ∙ 0 ∙ share

read it

Tie-Yan Liu

Featured Co-authors