Ya-Qin Zhang

Ya-Qin Zhang

Auto-generated profile, based on publicly available information

Ya-Qin Zhang

Tsinghua University

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

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

Representative Publications

View All Publications
26 January 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YLYang Liu
Yang Liu
YKYan Kang
Yan Kang
TZTianyuan Zou
Tianyuan Zou
YPYanhong Pu
Yanhong Pu
YHYuanqin He
Yuanqin He
QYQiang Yang
Qiang Yang
Vertical Federated Learning (VFL) is a federated learning setting where multiple parties with different features about the same set of users jointly train machine learning models without exposing their raw data or model parameters. Motivated by the rapid growth in VFL research and real-world applications, we provide a comprehensive review of the concept and algorithms of VFL, as well as current advances and challenges in various aspects, including effectiveness, efficiency, and privacy. We provide an exhaustive categorization for VFL settings and privacy-preserving protocols and comprehensively analyze the privacy attacks and defense strategies for each protocol. In the end, we propose a unified framework, termed VFLow, which considers the VFL problem under communication, computation, privacy, as well as effectiveness and fairness constraints. Finally, we review the most recent advances in industrial applications, highlighting open challenges and future directions for VFL.

29 May 2024
Verified
Conference Paper
Open access
HWHao Wen
Hao Wen
YLYuanchun Li
Yuanchun Li
GLGuohong Liu
Guohong Liu
SZShanhui Zhao
Shanhui Zhao
TYTao Yu
Tao Yu
YLYunxin Liu
Yunxin Liu
Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones. However, existing approaches suffer from poor scalability due to the limited language understanding ability and the non-trivial manual efforts required from developers or endusers. The recent advance of large language models (LLMs) in language understanding and reasoning inspires us to rethink the problem from a model-centric perspective, where task preparation, comprehension, and execution are handled by a unified language model. In this work, we introduce AutoDroid, a mobile task automation system capable of handling arbitrary tasks on any Android application without manual efforts. The key insight is to combine the commonsense knowledge of LLMs and domain-specific knowledge of apps through automated dynamic analysis. The main components include a functionality-aware UI representation method that bridges the UI with the LLM, exploration-based memory injection techniques that augment the app-specific domain knowledge of LLM, and a multi-granularity query optimization module that reduces the cost of model inference. We integrate AutoDroid with off-the-shelf LLMs including online GPT-4/GPT-3.5 and on-device Vicuna, and evaluate its performance on a new benchmark for memory-augmented Android task automation with 158 common tasks. The results demonstrated that AutoDroid is able to precisely generate actions with an accuracy of 90.9%, and complete tasks with a success rate of 71.3%, outperforming the GPT-4-powered baselines by 36.4% and 39.7%.

30 January 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JDJingliang Duan
Jingliang Duan
WWWenxuan Wang
Wenxuan Wang
LXLiming Xiao
Liming Xiao
JGJiaxin Gao
Jiaxin Gao
SLShengbo Li
Shengbo Li
KLKeqiang Li
Keqiang Li
Reinforcement learning (RL) has shown remarkable success in solving complex decision-making and control tasks. However, many model-free RL algorithms experience performance degradation due to inaccurate value estimation, particularly the overestimation of Q-values, which can lead to suboptimal policies. To address this issue, we previously proposed the Distributional Soft Actor-Critic (DSAC or DSACv1), an off-policy RL algorithm that enhances value estimation accuracy by learning a continuous Gaussian value distribution. Despite its effectiveness, DSACv1 faces challenges such as training instability and sensitivity to reward scaling, caused by high variance in critic gradients due to return randomness. In this paper, we introduce three key refinements to DSACv1 to overcome these limitations and further improve Q-value estimation accuracy: expected value substitution, twin value distribution learning, and variance-based critic gradient adjustment. The enhanced algorithm, termed DSAC with Three refinements (DSAC-T or DSACv2), is systematically evaluated across a diverse set of benchmark tasks. Without the need for task-specific hyperparameter tuning, DSAC-T consistently matches or outperforms leading model-free RL algorithms, including SAC, TD3, DDPG, TRPO, and PPO, in all tested environments. Additionally, DSAC-T ensures a stable learning process and maintains robust performance across varying reward scales. Its effectiveness is further demonstrated through real-world application in controlling a wheeled robot, highlighting its potential for deployment in practical robotic tasks.

19 July 2022 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
TZTianyuan Zou
Tianyuan Zou
YLYang Liu
Yang Liu
YKYan Kang
Yan Kang
WLWenhan Liu
Wenhan Liu
YHYuanqin He
Yuanqin He
YZYa-Qin Zhang
Ya-Qin Zhang
In a vertical federated learning (VFL) scenario where features and models are split into different parties, it has been shown that sample-level gradient information can be exploited to deduce crucial label information that should be kept secret. An immediate defense strategy is to protect sample-level messages communicated with Homomorphic Encryption (HE), exposing only batch-averaged local gradients to each party. In this paper, we show that even with HE-protected communication, private labels can still be reconstructed with high accuracy by gradient inversion attack, contrary to the common belief that batch-averaged information is safe to share under encryption. We then show that backdoor attack can also be conducted by directly replacing encrypted communicated messages without decryption. To tackle these attacks, we propose a novel defense method, Confusional AutoEncoder (termed CAE), which is based on autoencoder and entropy regularization to disguise true labels. To further defend attackers with sufficient prior label knowledge, we introduce DiscreteSGD-enhanced CAE (termed DCAE), and show that DCAE significantly boosts the main task accuracy than other known methods when defending various label inference attacks.

8 January 2026 in Science
Verified
Journal Article
Closed access
YJYinjun Jia
Yinjun Jia
BGBowen Gao
Bowen Gao
JTJiaxin Tan
Jiaxin Tan
JZJiqing Zheng
Jiqing Zheng
XHXin Hong
Xin Hong
YLYanyan Lan
Yanyan Lan
Recent breakthroughs in protein structure prediction have opened new avenues for genome-wide drug discovery, yet existing virtual screening methods remain computationally prohibitive. We present DrugCLIP, a contrastive learning framework that achieves ultrafast and accurate virtual screening, up to 10 million times faster than docking, while consistently outperforming various baselines on in silico benchmarks. In wet-lab validations, DrugCLIP achieved a 15% hit rate for norepinephrine transporter, and structures of two identified inhibitors were determined in complex with the target protein. For thyroid hormone receptor interactor 12, a target that lacks holo structures and small-molecule binders, DrugCLIP achieved a 17.5% hit rate using only AlphaFold2-predicted structures. Finally, we released GenomeScreenDB, an open-access database providing precomputed results for ~10,000 human proteins screened against 500 million compounds, pioneering a drug discovery paradigm in the post-AlphaFold era.

2 October 2023
Verified
Conference Paper
Open access
HWHao Wen
Hao Wen
YLYuanchun Li
Yuanchun Li
ZZZunshuai Zhang
Zunshuai Zhang
SJShiqi Jiang
Shiqi Jiang
XYXiaozhou Ye
Xiaozhou Ye
YLYunxin Liu
Yunxin Liu
Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable to generate tailored model architectures for different conditions. However, conventional pre-deployment model generation approaches are not satisfactory due to the difficulty of handling the diversity of edge environments and the demand for edge information. In this paper, we propose to adapt the model architecture after deployment in the target environment, where the model quality can be precisely measured and private edge data can be retained. To achieve efficient and effective edge model generation, we introduce a pretraining-assisted on-cloud model elastification method and an edge-friendly on-device architecture search method. Model elastification generates a high-quality search space of model architectures with the guidance of a developer-specified oracle model. Each subnet in the space is a valid model with different environment affinity, and each device efficiently finds and maintains the most suitable subnet based on a series of edge-tailored optimizations. Extensive experiments on various edge devices demonstrate that our approach is able to achieve significantly better accuracy-latency tradeoffs (e.g. 46.74% higher on average accuracy with a 60% latency budget) than strong baselines with minimal overhead (13 GPU hours in the cloud and 2 minutes on the edge server).