Author name cluster

Xiaodong Lin

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.

7 papers

1 author row

AAAI Conference 2024 Conference Paper

Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models

Ruichen Wang
Zekang Chen
Chen Chen
Jian Ma
Haonan Lu
Xiaodong Lin

Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited compositional capabilities, leading to attribute leakage, entity leakage, and missing entities. In this paper, we propose a novel attention mask control strategy based on predicted object boxes to address these issues. In particular, we first train a BoxNet to predict a box for each entity that possesses the attribute specified in the prompt. Then, depending on the predicted boxes, a unique mask control is applied to the cross- and self-attention maps. Our approach produces a more semantically accurate synthesis by constraining the attention regions of each token in the prompt to the image. In addition, the proposed method is straightforward and effective and can be readily integrated into existing cross-attention-based T2I generators. We compare our approach to competing methods and demonstrate that it can faithfully convey the semantics of the original text to the generated content and achieve high availability as a ready-to-use plugin. Please refer to https://github.com/OPPO-Mente-Lab/attention-mask-control.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks

Haonan Yan
Wenjing Zhang
Qian Chen
Xiaoguang Li
Wenhai Sun
Hui Li
Xiaodong Lin

Model poisoning attacks greatly jeopardize the application of federated learning (FL). The effectiveness of existing defenses is susceptible to the latest model poisoning attacks, leading to a decrease in prediction accuracy. Besides, these defenses are intractable to distinguish benign outliers from malicious gradients, which further compromises the model generalization. In this work, we propose a novel defense including detection and aggregation, named RECESS, to serve as a “vaccine” for FL against model poisoning attacks. Different from the passive analysis in previous defenses, RECESS proactively queries each participating client with a delicately constructed aggregation gradient, accompanied by the detection of malicious clients according to their responses with higher accuracy. Further, RECESS adopts a newly proposed trust scoring based mechanism to robustly aggregate gradients. Rather than previous methods of scoring in each iteration, RECESS takes into account the correlation of clients’ performance over multiple iterations to estimate the trust score, bringing in a significant increase in detection fault tolerance. Finally, we extensively evaluate RECESS on typical model architectures and four datasets under various settings including white/black-box, cross-silo/device FL, etc. Experimental results show the superiority of RECESS in terms of reducing accuracy loss caused by the latest model poisoning attacks over five classic and two state-of-the-art defenses.

PDF Details

IJCAI Conference 2022 Conference Paper

ARCANE: An Efficient Architecture for Exact Machine Unlearning

Haonan Yan
Xiaoguang Li
Ziyao Guo
Hui Li
Fenghua Li
Xiaodong Lin

Recently users’ right-to-be-forgotten is stipulated by many laws and regulations. However, only removing the data from the dataset is not enough, as machine learning models would memorize the training data once the data is involved in model training, increasing the risk of exposing users’ privacy. To solve this problem, currently, the straightforward method, naive retraining, is to discard these data and retrain the model from scratch, which is reliable but brings much computational and time overhead. In this paper, we propose an exact unlearning architecture called ARCANE. Based on ensemble learning, we transform the naive retraining into multiple one-class classiﬁcation tasks to reduce retraining cost while ensuring model performance, especially in the case of a large number of unlearning requests not considered by previous works. Then we further introduce data preprocessing methods to reduce the retraining overhead and speed up the unlearning, which includes representative data selection for redundancy removal, training state saving to reuse previous calculation results, and sorting to cope with unlearning requests of different distributions. We extensively evaluate ARCANE on three typical datasets with three common model architectures. Experiment results show the effectiveness and superiority of ARCANE over both the naive retraining and the state-of-the-art method in terms of model performance and unlearning speed.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Learning to Walk with Dual Agents for Knowledge Graph Reasoning

Denghui Zhang
Zixuan Yuan
Hao Liu
Xiaodong Lin
Hui Xiong

Graph walking based on reinforcement learning (RL) has shown great success in navigating an agent to automatically complete various reasoning tasks over an incomplete knowledge graph (KG) by exploring multi-hop relational paths. However, existing multi-hop reasoning approaches only work well on short reasoning paths and tend to miss the target entity with the increasing path length. This is undesirable for many reasoning tasks in real-world scenarios, where short paths connecting the source and target entities are not available in incomplete KGs, and thus the reasoning performances drop drastically unless the agent is able to seek out more clues from longer paths. To address the above challenge, in this paper, we propose a dual-agent reinforcement learning framework, which trains two agents (GIANT and DWARF) to walk over a KG jointly and search for the answer collaboratively. Our approach tackles the reasoning challenge in long paths by assigning one of the agents (GIANT) searching on cluster-level paths quickly and providing stage-wise hints for another agent (DWARF). Finally, experimental results on several KG reasoning benchmarks show that our approach can search answers more accurately and efficiently, and outperforms existing RL-based methods for long path queries by a large margin.

PDF Details

JMLR Journal 2014 Journal Article

Alternating Linearization for Structured Regularization Problems

Xiaodong Lin
Minh Pham
Andrzej Ruszczyński

We adapt the alternating linearization method for proximal decomposition to structured regularization problems, in particular, to the generalized lasso problems. The method is related to two well-known operator splitting methods, the Douglas--Rachford and the Peaceman--Rachford method, but it has descent properties with respect to the objective function. This is achieved by employing a special update test, which decides whether it is beneficial to make a Peaceman--Rachford step, any of the two possible Douglas--Rachford steps, or none. The convergence mechanism of the method is related to that of bundle methods of nonsmooth optimization. We also discuss implementation for very large problems, with the use of specialized algorithms and sparse data structures. Finally, we present numerical results for several synthetic and real-world examples, including a three-dimensional fused lasso problem, which illustrate the scalability, efficacy, and accuracy of the method. [abs] [ pdf ][ bib ] &copy JMLR 2014. ( edit, beta )

PDF Details

JBHI Journal 2014 Journal Article

Exploiting Geo-Distributed Clouds for a E-Health Monitoring System With Minimum Service Delay and Privacy Preservation

Qinghua Shen
Xiaohui Liang
Xuemin Shen
Xiaodong Lin
Henry Y. Luo

We propose an e-health monitoring system with minimum service delay and privacy preservation by exploiting geo-distributed clouds. In the system, the resource allocation scheme enables the distributed cloud servers to cooperatively assign the servers to the requested users under the load balance condition. Thus, the service delay for users is minimized. In addition, a traffic-shaping algorithm is proposed. The traffic-shaping algorithm converts the user health data traffic to the nonhealth data traffic such that the capability of traffic analysis attacks is largely reduced. Through the numerical analysis, we show the efficiency of the proposed traffic-shaping algorithm in terms of service delay and privacy preservation. Furthermore, through the simulations, we demonstrate that the proposed resource allocation scheme significantly reduces the service delay compared to two other alternatives using jointly the short queue and distributed control law.

Details DOI

IS Journal 2013 Journal Article

A Lightweight Conditional Privacy-Preservation Protocol for Vehicular Traffic-Monitoring Systems

Rongxing Lu
Xiaodong Lin
Zhiguo Shi
Xuemin Sherman Shen

Vehicular traffic monitoring (VTM) is a promising cyber-physical system, but it faces many security and privacy challenges. Here, a new lightweight conditional privacy preservation (LCPP) protocol utilizes simple hash-chain techniques to secure VTM systems. The protocol not only supports the requirement of conditional privacy preservation, but also achieves efficient local revocation verification on the road.

Details DOI