Jia Wang

Jia Wang


Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 December 2022 in IEEE Journal on Selected Areas in Information Theory
Verified
Journal Article
Closed access
Jun ChenJun Chen
Jun Chen
LYLei Yu
Lei Yu
JWJia Wang
Jia Wang
WSWuxian Shi
Wuxian Shi
YGYiqun Ge
Yiqun Ge
WTWen Tong
Wen Tong
Rate-distortion-perception theory generalizes Shannon’s rate-distortion theory by introducing a constraint on the perceptual quality of the output. The perception constraint complements the conventional distortion constraint and aims to enforce distribution-level consistencies. In this new theory, the information-theoretic limit is characterized by the rate-distortion-perception function. Although a coding theorem for the rate-distortion-perception function has recently been established, the fundamental nature of the optimal coding schemes remains unclear, especially regarding the role of randomness in encoding and decoding. It is shown in the present work that except for certain extreme cases, the rate-distortion-perception function is achievable by deterministic codes. This paper also clarifies the subtle differences between two notions of perfect perceptual quality and explores some alternative formulations of the perception constraint.

28 February 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
TZTianyi Zheng
Tianyi Zheng
BLBo Li
Bo Li
SWShuang Wu
Shuang Wu
BWBen Wan
Ben Wan
GMGuodong Mu
Guodong Mu
JWJia Wang
Jia Wang
The generalizable face anti-spoofing (FAS) has attracted much attention recently. Even though many existing methods perform well under intra-domain settings, the model’s performance in the unseen domain is not satisfying. In this paper, we shift our attention to the frequency domain to seek a solution. Specifically, we examine the characteristics of different frequency band components of FAS images and observe that the model’s cross-domain performance is very sensitive to low-frequency features. To alleviate this sensitivity and improve the model’s performance in FAS cross-domain tasks, we propose a new approach called Masked Frequency Autoencoders (MFAE). MFAE randomly masks a portion of frequencies on the low-frequency spectrum of the image and then reconstructs the image from the resulting embedding. This innovative Masked Image Modeling (MIM) strategy can be used as a self-supervised task for pre-training vision transformers (ViTs), which can reduce the ViT encoder’s sensitivity to domain shifts. Additionally, we add an auxiliary content-regularization decoder in our MFAE to encourage the encoder to be insensitive to low-frequency features. The results show that the model insensitive to low-frequency features performs well on extensive public datasets and outperforms other state-of-the-art methods in cross-domain FAS tasks.

20 September 2022 in IEEE Communications Letters
Verified
Journal Article
Closed access
NZNaifu Zhang
Naifu Zhang
Meixia TaoMeixia Tao
Meixia Tao
JWJia Wang
Jia Wang
SSShuo Shao
Shuo Shao
This letter introduces a new coded transmission design for model aggregation in federated learning (FL) over Gaussian multiple access channels (MAC), named coded over-the-air computation (codedAirComp). It enjoys the optimality of analog AirComp-based uncoded transmission for fast model aggregation, but also leverages the traditional source-channel separation principle for more practical uses. Specifically, the proposed codedAirComp employs stochastic uniform quantization for local gradient compression and nested lattice coding for channel transmission. Compared with the traditional coding scheme, the proposed scheme significantly reduces the model aggregation distortion and improves the overall learning accuracy.

6 January 2020 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
JZJiahe Zhang
Jiahe Zhang
XMXiongkuo Min
Xiongkuo Min
JJJun Jia
Jun Jia
ZZZehao Zhu
Zehao Zhu
JWJia Wang
Jia Wang
GZGuangtao Zhai
Guangtao Zhai

28 November 2022 in IEEE Transactions on Communications
Verified
Journal Article
Closed access
NZNaifu Zhang
Naifu Zhang
Meixia TaoMeixia Tao
Meixia Tao
JWJia Wang
Jia Wang
FXFan Xu
Fan Xu
One of the main focuses in distributed learning is communication efficiency, since model aggregation at each round of training can consist of millions to billions of parameters. Several model compression methods, such as gradient quantization and sparsification, have been proposed to improve the communication efficiency of model aggregation. However, the information-theoretic minimum communication cost for a given distortion of gradient estimators is still unknown. In this paper, we study the fundamental limit of communication cost of model aggregation in distributed learning from a rate-distortion perspective. By formulating the model aggregation as a vector Gaussian CEO problem, we derive the rate region bound and sum-rate-distortion function for the model aggregation problem, which reveals the minimum communication rate at a particular gradient distortion upper bound. We also analyze the communication cost at each iteration and total communication cost based on the sum-rate-distortion function with the gradient statistics of real-world datasets. It is found that the communication gain by exploiting the correlation between worker nodes is significant for SignSGD, and a high distortion of gradient estimator can achieve low total communication cost in gradient compression.

28 October 2024
Verified
Book Chapter
Closed access
PDF file
TZTianyi Zheng
Tianyi Zheng
PJPeng-Tao Jiang
Peng-Tao Jiang
BWBen Wan
Ben Wan
HZHao Zhang
Hao Zhang
JCJinwei Chen
Jinwei Chen
BLBo Li
Bo Li