Tie-Yan Liu

is this you? claim profile

∙ 0 followers
Microsoft

Principal Research Manager at Microsoft Research Asia

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. ∙ 0 ∙ 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
Dual Learning: Theoretical Study and an Algorithmic Extension

Dual learning has been successfully applied in many machine learning app...
05/17/2020 ∙ by Zhibing Zhao, et al. ∙ 0 ∙ share

read it
Invertible Image Rescaling

High-resolution digital images are usually downscaled to fit various dis...
05/12/2020 ∙ by Mingqing Xiao, et al. ∙ 8 ∙ share

read it
SEEK: Segmented Embedding of Knowledge Graphs

In recent years, knowledge graph embedding becomes a pretty hot research...
05/02/2020 ∙ by Wentao Xu, et al. ∙ 8 ∙ share

read it
LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning

While pre-training and fine-tuning, e.g., BERT <cit.>, GPT-2 <cit.>, hav...
04/27/2020 ∙ by Kaitao Song, et al. ∙ 0 ∙ share

read it
A Study of Non-autoregressive Model for Sequence Generation

Non-autoregressive (NAR) models generate all the tokens of a sequence in...
04/22/2020 ∙ by Yi Ren, et al. ∙ 0 ∙ share

read it
MPNet: Masked and Permuted Pre-training for Language Understanding

BERT adopts masked language modeling (MLM) for pre-training and is one o...
04/20/2020 ∙ by Kaitao Song, et al. ∙ 0 ∙ share

read it
Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator

Generative Adversarial Networks (GANs) have shown great promise in model...
04/05/2020 ∙ by Yuxuan Song, et al. ∙ 0 ∙ share

read it
Suphx: Mastering Mahjong with Deep Reinforcement Learning

Artificial Intelligence (AI) has achieved great success in many domains,...
03/30/2020 ∙ by Junjie Li, et al. ∙ 0 ∙ share

read it
Semi-Supervised Neural Architecture Search

Neural architecture search (NAS) relies on a good controller to generate...
02/24/2020 ∙ by Renqian Luo, et al. ∙ 0 ∙ share

read it
Incorporating BERT into Neural Machine Translation

The recently proposed BERT has shown great power on a variety of natural...
02/17/2020 ∙ by Jinhua Zhu, et al. ∙ 0 ∙ share

read it
On Layer Normalization in the Transformer Architecture

The Transformer is widely used in natural language processing tasks. To ...
02/12/2020 ∙ by Ruibin Xiong, et al. ∙ 0 ∙ share

read it
A Study of Multilingual Neural Machine Translation

Multilingual neural machine translation (NMT) has recently been investig...
12/25/2019 ∙ by Xu Tan, et al. ∙ 0 ∙ share

read it
Gradient Perturbation is Underrated for Differentially Private Convex Optimization

Gradient perturbation, widely used for differentially private optimizati...
11/26/2019 ∙ by Da Yu, et al. ∙ 0 ∙ share

read it
Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation

Non-autoregressive translation (NAT) models remove the dependence on pre...
11/20/2019 ∙ by Junliang Guo, et al. ∙ 0 ∙ share

read it
Microsoft Research Asia's Systems for WMT19

We Microsoft Research Asia made submissions to 11 language directions in...
11/07/2019 ∙ by Yingce Xia, et al. ∙ 0 ∙ share

read it
Distributional Reward Decomposition for Reinforcement Learning

Many reinforcement learning (RL) tasks have specific properties that can...
11/06/2019 ∙ by Zichuan Lin, et al. ∙ 38 ∙ share

read it
Hint-Based Training for Non-Autoregressive Machine Translation

Due to the unparallelizable nature of the autoregressive factorization, ...
09/15/2019 ∙ by Zhuohan Li, et al. ∙ 0 ∙ share

read it
Self-paced Ensemble for Highly Imbalanced Massive Data Classification

Many real-world applications reveal difficulties in learning classifiers...
09/08/2019 ∙ by Zhining Liu, et al. ∙ 1 ∙ share

read it
Training Effective Ensemble on Imbalanced Data by Self-paced Harmonizing Classification Hardness

Many real-world applications reveal difficulties in learning classifiers...
09/08/2019 ∙ by Zhining Liu, et al. ∙ 0 ∙ share

read it
Multilingual Neural Machine Translation with Language Clustering

Multilingual neural machine translation (NMT), which translates multiple...
08/25/2019 ∙ by Xu Tan, et al. ∙ 0 ∙ share

read it
Representation Degeneration Problem in Training Natural Language Generation Models

We study an interesting problem in training neural network-based models ...
07/28/2019 ∙ by Jun Gao, et al. ∙ 0 ∙ share

read it

Tie-Yan Liu

Featured Co-authors