Shuo Yang

Shuo Yang

Auto-generated profile, based on publicly available information

Shuo Yang

Harbin Institute of Technology (Shenzhen), Shenzhen, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
10 July 2024
Verified
Conference Paper
Open access
XLXinyu Lin
Xinyu Lin
WWWenjie Wang
Wenjie Wang
YLYongqi Li
Yongqi Li
SYShuo Yang
Shuo Yang
Fuli FengFuli Feng
Fuli Feng
TCTat-Seng Chua
Tat-Seng Chua
Leveraging Large Language Models (LLMs) for recommendation has recently garnered considerable attention, where fine-tuning plays a key role in LLMs' adaptation. However, the cost of fine-tuning LLMs on rapidly expanding recommendation data limits their practical application. To address this challenge, few-shot fine-tuning offers a promising approach to quickly adapt LLMs to new recommendation data. We propose the task of data pruning for efficient LLM-based recommendation, aimed at identifying representative samples tailored for LLMs' few-shot fine-tuning. While coreset selection is closely related to the proposed task, existing coreset selection methods often rely on suboptimal heuristic metrics or entail costly optimization on large-scale recommendation data. To tackle these issues, we introduce two primary objectives for the data pruning task in the context of LLM-based recommendation: 1) high accuracy aims to identify the influential samples that can lead to high overall performance; and 2) high efficiency underlines the low costs of the data pruning process. To pursue the two objectives, we propose a novel data pruning method incorporating two scores, namely influence score and effort score, to efficiently identify the influential samples. Particularly, the influence score is introduced to accurately estimate the influence of removing each sample on the overall performance. To achieve low costs of the data pruning process, we employ a small-sized surrogate model to replace LLMs to obtain the influence score. Considering the potential gap between the surrogate model and LLMs, we further propose an effort score to prioritize some hard samples specifically for LLMs. We instantiate the proposed method on two competitive LLM-based recommender models, and empirical results on three real-world datasets validate the effectiveness of our proposed method. In particular, our method uses only 2% samples to surpass the full data fine-tuning, reducing time costs by 97%.

29 March 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
BDBosheng Ding
Bosheng Ding
RZRuiheng Zhang
Ruiheng Zhang
LXLixin Xu
Lixin Xu
GLGuanyu Liu
Guanyu Liu
SYShuo Yang
Shuo Yang
QZQi Zhang
Qi Zhang
Hazy images captured under ill-posed scenarios with scattering medium (i.e. haze, fog, or smoke) are contaminated in visibility. Inevitably, these images are further degraded by noises owing to real-world imaging. Most existing hazy image enhancement methods perform image dehazing and denoising stage by stage, with the undesirable result that the estimation error of the former stage has to be propagated and amplified in the latter stage, e.g., noise amplification after dehazing. To address this inconsistent degradation, we present an Unsupervised Unified Image Dehazing and Denoising Network, U 2 D 2 Net, to remove the haze and suppress the noise simultaneously for a single hazy image. U 2 D 2 Net is mainly comprised of an unsupervised dehazing module, an unsupervised denoising module, and a regionsimilarity fusion strategy. Specifically, we propose an unsupervised transmission-aware dehazing module to restore visibility and suppress depth-dependent noise propagation in the dehazing module. Besides, we design an unsupervised network with a Mean/Max Sub-Sampler in the denoising module. To exploit the correlation and complementary between the previous outputs, a region-similarity fusion strategy is developed to compute the final qualified result. Extensive experiments on both synthetic and realworld datasets illustrate that U 2 D 2 Net outperforms other stateof-the-art dehazing and denoising methods in terms of PSNR, SSIM, and subjective visual effects.

3 December 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SYShuo Yang
Shuo Yang
SWSonghua Wu
Songhua Wu
TLTongliang Liu
Tongliang Liu
MXMin Xu
Min Xu
A major gap between few-shot and many-shot learning is the data distribution empirically oserved by the model during training. In few-shot learning, the learned model can easily become over-fitted based on the biased distribution formed by only a few training examples, while the ground-truth data distribution is more accurately uncovered in many-shot learning to learn a well-generalized model. In this paper, we propose to calibrate the distribution of these few-sample classes to be more unbiased to alleviate such an over-fitting problem. The distribution calibration is achieved by transferring statistics from the classes with sufficient examples to those few-sample classes. After calibration, an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier. Specifically, we assume every dimension in the feature representation from the same class follows a Gaussian distribution so that the mean and the variance of the distribution can borrow from that of similar classes whose statistics are better estimated with an adequate number of samples. Extensive experiments on three datasets, mini ImageNet, tiered ImageNet, and CUB, show that a simple linear classifier trained using the features sampled from our calibrated distribution can outperform the state-of-the-art accuracy by a large margin. Besides the favorable performance, the proposed method also exhibits high flexibility by showing consistent accuracy improvement when it is built on top of any off-the-shelf pretrained feature extractors and classification models without extra learnable parameters. The visualization of these generated features demonstrates that our calibrated distribution is an accurate estimation thus the generalization ability gain is convincing. We also establish a generalization error bound for the proposed distribution-calibration-based few-shot learning, which consists of the distribution assumption error , the distribution approximation error , and the estimation error . This generalization error bound theoretically justifies the effectiveness of the proposed method.

8 January 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
RZRuiheng Zhang
Ruiheng Zhang
Zhe CaoZhe Cao
Zhe Cao
SYShuo Yang
Shuo Yang
LSLingyu Si
Lingyu Si
HSHaoyang Sun
Haoyang Sun
FSFuchun Sun
Fuchun Sun
The label transition matrix has emerged as a widely accepted method for mitigating label noise in machine learning. In recent years, numerous studies have centered on leveraging deep neural networks to estimate the label transition matrix for individual instances within the context of instance-dependent noise. However, these methods suffer from low search efficiency due to the large space of feasible solutions. Behind this drawback, we have explored that the real murderer lies in the invalid class transitions, that is, the actual transition probability between certain classes is zero but is estimated to have a certain value. To mask the invalid class transitions , we introduced a human-cognition-assisted method with structural information from human cognition. Specifically, we introduce a structured transition matrix network ( STMN ) designed with an adversarial learning process to balance instance features and prior information from human cognition. The proposed method offers two advantages: 1) better estimation effectiveness is obtained by sparing the transition matrix and 2) better estimation accuracy is obtained with the assistance of human cognition. By exploiting these two advantages, our method parametrically estimates a sparse label transition matrix, effectively converting noisy labels into true labels. The efficiency and superiority of our proposed method are substantiated through comprehensive comparisons with state-of-the-art methods on three synthetic datasets and a real-world dataset. Our code will be available at https://github.com/WheatCao/STMN-Pytorch.

19 May 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
JXJiahao Xia
Jiahao Xia
Haimin ZhangHaimin Zhang
Haimin Zhang
Shiping WenShiping Wen
Shiping Wen
SYShuo Yang
Shuo Yang
MXMin Xu
Min Xu

4 August 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SYShuo Yang
Shuo Yang
SWSonghua Wu
Songhua Wu
EYErkun Yang
Erkun Yang
BHBo Han
Bo Han
YLYang Liu
Yang Liu
TLTongliang Liu
Tongliang Liu
In label-noise learning, estimating the transition matrix is a hot topic as the matrix plays an important role in building statistically consistent classifiers . Traditionally, the transition from clean labels to noisy labels (i.e., clean-label transition matrix (CLTM) ) has been widely exploited on class-dependent label-noise (wherein all samples in a clean class share the same label transition matrix). However, the CLTM cannot handle the more common instance-dependent label-noise well (wherein the clean-to-noisy label transition matrix needs to be estimated at the instance level by considering the input quality). Motivated by the fact that classifiers mostly output Bayes optimal labels for prediction, in this paper, we study to directly model the transition from Bayes optimal labels to noisy labels (i.e., Bayes-Label Transition Matrix (BLTM) ) and learn a classifier to predict Bayes optimal labels . Note that given only noisy data, it is ill-posed to estimate either the CLTM or the BLTM . But favorably, Bayes optimal labels have no uncertainty compared with the clean labels, i.e., the class posteriors of Bayes optimal labels are one-hot vectors while those of clean labels are not. This enables two advantages to estimate the BLTM , i.e., (a) a set of examples with theoretically guaranteed Bayes optimal labels can be collected out of noisy data; (b) the feasible solution space is much smaller. By exploiting the advantages, this work proposes a parametrical model for estimating the instance-dependent label-noise transition matrix by employing a deep neural network , leading to better generalization and superior classification performance.