Author name cluster

Yangyang Shen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

ICML Conference 2025 Conference Paper

Bi-perspective Splitting Defense: Achieving Clean-Seed-Free Backdoor Security

Yangyang Shen
Xiao Tan 0005
Dian Shen
Meng Wang 0009
Beilun Wang

Backdoor attacks have seriously threatened deep neural networks (DNNs) by embedding concealed vulnerabilities through data poisoning. To counteract these attacks, training benign models from poisoned data garnered considerable interest from researchers. High-performing defenses often rely on additional clean subsets/seeds, which is untenable due to increasing privacy concerns and data scarcity. In the absence of additional clean subsets/seeds, defenders resort to complex feature extraction and analysis, resulting in excessive overhead and compromised performance. To address these challenges, we identify the key lies in sufficient utilization of both the easier-to-obtain target labels and clean hard samples. In this work, we propose a Bi-perspective Splitting Defense (BSD). BSD distinguishes clean samples using both semantic and loss statistics characteristics through open set recognition-based splitting (OSS) and altruistic model-based data splitting (ALS) respectively. Through extensive experiments on benchmark datasets and against representative attacks, we empirically demonstrate that BSD surpasses existing defenses by over 20% in average Defense Effectiveness Rating (DER), achieving clean data-free backdoor security.

Details

NeurIPS Conference 2024 Conference Paper

FasMe: Fast and Sample-efficient Meta Estimator for Precision Matrix Learning in Small Sample Settings

Xiao Tan
Yiqin Wang
Yangyang Shen
Dian Shen
Meng Wang
Peibo Duan
Beilun Wang

Precision matrix estimation is a ubiquitous task featuring numerous applications such as rare disease diagnosis and neural connectivity exploration. However, this task becomes challenging in small sample settings, where the number of samples is significantly less than the number of dimensions, leading to unreliable estimates. Previous approaches either fail to perform well in small sample settings or suffer from inefficient estimation processes, even when incorporating meta-learning techniques. To this end, we propose a novel approach FasMe for Fast and Sample-efficient Meta Precision Matrix Learning, which first extracts meta-knowledge through a multi-task learning diagram. Then, meta-knowledge constraints are applied using a maximum determinant matrix completion algorithm for the novel task. As a result, we reduce the sample size requirements to $O(\log p/K)$ per meta-training task and $O(\log\vert \mathcal{G}\vert)$ for the meta-testing task. Moreover, the hereby proposed model only needs $O(p \log\epsilon^{-1})$ time and $O(p)$ memory for converging to an $\epsilon$-accurate solution. On multiple synthetic and biomedical datasets, FasMe is at least ten times faster than the four baselines while promoting prediction accuracy in small sample settings.

PDF Details DOI

EAAI Journal 2024 Journal Article

Improved differential evolution algorithm based on cooperative multi-population

Yangyang Shen
Jing Wu
Minfu Ma
Xiaofeng Du
Hao Wu
Xianlong Fei
Datian Niu

This paper introduces an improved differential evolution algorithm based on cooperative multi-population (CMp-DE for short), which combines diverse population collaboration mechanisms and catalytic factors into an improved differential evolution framework. By harnessing various population collaboration mechanisms, the algorithm enhances the diversity of individuals within populations during initial iterations and reduces it during later iterations, thereby harmonizing the algorithm's exploratory and exploitative capabilities. Furthermore, a novel mutation operator is proposed that divides the iterative process into exploration and exploitation phases, thereby augmenting the algorithm's global exploration prowess. Lastly, a catalytic operator is introduced to generate new individuals near post-crossover individuals based on a specified rule, which enhances the algorithm's ability to escape local optima and increasing stability. The proposed CMp-DE is benchmarked against the CEC2017 benchmark test functions and compared against 13 algorithms, including five differential evolution algorithms and their variants, as well as eight state-of-the-art metaheuristic optimization algorithms. This evaluation assesses the CMp-DE's solution accuracy, convergence, stability, and scalability. Finally, the applicability of CMp-DE is validated by addressing six practical optimization problems. The experimental results show that CMp-DE surpasses other algorithms in terms of both convergence accuracy and robustness. Moreover, integrating a catalytic operator with other optimization algorithms notably boosts performance in convergence accuracy and stability. The inclusion of the catalytic operator has significantly enhanced the performance of algorithms compared to their performance before its addition. This underscores the potential of the catalytic operator in improving the performance of various algorithms, particularly in terms of convergence accuracy and robustness.

Details DOI