51 citations · 137 across the 26 of their papers we have counts for
26 papers
On the Calibration and Uncertainty with Pólya-Gamma Augmentation for Dialog Retrieval Models
Tong Ye, Shijing Si, Jianzong Wang +3
Deep neural retrieval models have amply demonstrated their power but estimating the reliability of their predictions remains challenging. Most dialog response retrieval models outp…
Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization
Zexuan Qiu, Qinliang Su, Jianxing Yu +1
Efficient document retrieval heavily relies on the technique of semantic hashing, which learns a binary code for every document and employs Hamming distance to evaluate document di…
Pushing the Efficiency Limit Using Structured Sparse Convolutions
Vinay Kumar Verma, Nikhil Mehta, Shijing Si +2
Weight pruning is among the most popular approaches for compressing deep convolutional neural networks. Recent work suggests that in a randomly initialized deep neural network, the…
Pose Guided Human Image Synthesis with Partially Decoupled GAN
Jianhan Wu, Jianzong Wang, Shijing Si +2
Pose Guided Human Image Synthesis (PGHIS) is a challenging task of transforming a human image from the reference pose to a target pose while preserving its style. Most existing met…
Machine Unlearning Method Based On Projection Residual
Zihao Cao, Jianzong Wang, Shijing Si +2
Machine learning models (mainly neural networks) are used more and more in real life. Users feed their data to the model for training. But these processes are often one-way. Once t…
RL-MD: A Novel Reinforcement Learning Approach for DNA Motif Discovery
Wen Wang, Jianzong Wang, Shijing Si +2
The extraction of sequence patterns from a collection of functionally linked unlabeled DNA sequences is known as DNA motif discovery, and it is a key task in computational biology.…
Boosting Star-GANs for Voice Conversion with Contrastive Discriminator
Shijing Si, Jianzong Wang, Xulong Zhang +3
Nonparallel multi-domain voice conversion methods such as the StarGAN-VCs have been widely applied in many scenarios. However, the training of these models usually poses a challeng…
Debias the Black-box: A Fair Ranking Framework via Knowledge Distillation
Zhitao Zhu, Shijing Si, Jianzong Wang +2
Deep neural networks can capture the intricate interaction history information between queries and documents, because of their many complicated nonlinear units, allowing them to pr…
Uncertainty Calibration for Deep Audio Classifiers
Tong Ye, Shijing Si, Jianzong Wang +2
Although deep Neural Networks (DNNs) have achieved tremendous success in audio classification tasks, their uncertainty calibration are still under-explored. A well-calibrated model…
Leveraging Causal Inference for Explainable Automatic Program Repair
Jianzong Wang, Shijing Si, Zhitao Zhu +3
Deep learning models have made significant progress in automatic program repair. However, the black-box nature of these methods has restricted their practical applications. To addr…
A Fair Federated Learning Framework With Reinforcement Learning
Yaqi Sun, Shijing Si, Jianzong Wang +3
Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. H…
Federated Non-negative Matrix Factorization for Short Texts Topic Modeling with Mutual Information
Shijing Si, Jianzong Wang, Ruiyi Zhang +2
Non-negative matrix factorization (NMF) based topic modeling is widely used in natural language processing (NLP) to uncover hidden topics of short text documents. Usually, training…
Cali3F: Calibrated Fast Fair Federated Recommendation System
Zhitao Zhu, Shijing Si, Jianzong Wang +1
The increasingly stringent regulations on privacy protection have sparked interest in federated learning. As a distributed machine learning framework, it bridges isolated data isla…
Augmentation-induced Consistency Regularization for Classification
Jianhan Wu, Shijing Si, Jianzong Wang +1
Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many resear…
Improving Human Image Synthesis with Residual Fast Fourier Transformation and Wasserstein Distance
Jianhan Wu, Shijing Si, Jianzong Wang +1
With the rapid development of the Metaverse, virtual humans have emerged, and human image synthesis and editing techniques, such as pose transfer, have recently become popular. Mos…
Towards Speaker Age Estimation with Label Distribution Learning
Shijing Si, Jianzong Wang, Junqing Peng +1
Existing methods for speaker age estimation usually treat it as a multi-class classification or a regression problem. However, precise age identification remains a challenge due to…
VU-BERT: A Unified framework for Visual Dialog
Tong Ye, Shijing Si, Jianzong Wang +3
The visual dialog task attempts to train an agent to answer multi-turn questions given an image, which requires the deep understanding of interactions between the image and dialog…
Speech2Video: Cross-Modal Distillation for Speech to Video Generation
Shijing Si, Jianzong Wang, Xiaoyang Qu +4
This paper investigates a novel task of talking face video generation solely from speeches. The speech-to-video generation technique can spark interesting applications in entertain…
Variational Information Bottleneck for Effective Low-resource Audio Classification
Shijing Si, Jianzong Wang, Huiming Sun +6
Large-scale deep neural networks (DNNs) such as convolutional neural networks (CNNs) have achieved impressive performance in audio classification for their powerful capacity and st…
FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders
Pengyu Cheng, Weituo Hao, Siyang Yuan +2
Pretrained text encoders, such as BERT, have been applied increasingly in various natural language processing (NLP) tasks, and have recently demonstrated significant performance ga…
Reinforcement Learning for Flexibility Design Problems
Yehua Wei, Lei Zhang, Ruiyi Zhang +3
Flexibility design problems are a class of problems that appear in strategic decision-making across industries, where the objective is to design a (, manufacturing) network t…
Students Need More Attention: BERT-based AttentionModel for Small Data with Application to AutomaticPatient Message Triage
Shijing Si, Rui Wang, Jedrek Wosik +5
Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models. So motivated, we propose a novel framework…
Scalable Control Variates for Monte Carlo Methods via Stochastic Optimization
Shijing Si, Chris. J. Oates, Andrew B. Duncan +2
Control variates are a well-established tool to reduce the variance of Monte Carlo estimators. However, for large-scale problems including high-dimensional and large-sample setting…
Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding
Dhanasekar Sundararaman, Vivek Subramanian, Guoyin Wang +4
Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates…