报告题目1：Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation
报告题目2：Quick and Accurate False Data Detection in Mobile Crowd Sensing
报告人：WANG XIN
报告时间：2019年6月17日上午9:30
报告地点：地质宫330海光学术报告厅
主办单位：仪器科学与电气工程学院
Dr. Wang is currently the director of the Wireless Networking and Systems lab of the department of Electrical and Computer Engineering of the State University of New York (SUNY) at Stony Brook. She was a Member of Technical Staff in the area of mobile and wireless networking at Bell Labs Research, Lucent Technologies, New Jersey between 2001 and 2003. Dr. Wang has been conducting and leading research work in the design of network architectures, protocols and algorithms. The work of her group falls into a few directions, including advanced wireless network architecture, mobile cloud computing and distributed computing, and big data analysis and deep learning. Dr. Wang obtained her PhD from Columbia University, BS and MS from Beijing University of Post and Telecommunications, respectively. She is a recipient of NSF career award in 2005 and the ONR Chief of Naval Research (CNR) Challenge award in 2011.
She currently serves as an associate editor of IEEE Transactions of Mobile Computing (TMC). She also serves TPC chair or program committee members in many technical conferences, including ACM MobiCom, IEEE Infocom, IEEE ICDCS, and IEEE PerCom. Her research group has published more than 100 papers in highly reputed conferences and journals, including ACM Sigmetrics, ACM MobiCom, USENIX NSDI, IEEE ICNP, IEEE Infocom, IEEE ICDCS, IEEE Percom, IEEE TON, IEEE TMC, IEEE JSAC, IEEE TC, and IEEE TDSC.
Abstract1: State-of-the-art techniques in Generative Adversarial Networks (GANs) have shown remarkable success in image-to-image translation from peer domain X to domain Y using paired image data. However, obtaining abundant paired data is a non-trivial and expensive process in the majority of applications. When there is a need to translate images across n domains, if the training is performed between every two domains, the complexity of the training will increase quadratically. Moreover, training with data from two domains only at a time cannot benefit from data of other domains, which prevents the extraction of more useful features and hinders the progress of this research area. In this work, we propose a general framework for unsupervised image-to-image translation across multiple domains, which can translate images from domain X to any a domain without requiring direct training between the two domains involved in image translation. A byproduct of the framework is the reduction of computing time and computing resources, since it needs less time than training the domains in pairs as is done in state-of-the-art work. Our proposed framework consists of a pair of encoders along with a pair of GANs which learns high-level features across different domains to generate diverse and realistic samples from. Our framework shows competing results on many image-to-image tasks compared with state-of-the-art techniques.
Abstract2: With the proliferation of smartphones, a novel sensing paradigm called Mobile Crowd Sensing (MCS) has emerged very recently. However, the attacks and faults in MCS cause a serious false data problem. Observing the intrinsic low dimensionality of general monitoring data and the sparsity of false data, false data detection can be performed based on the separation of normal data and anomalies. Although the existing separation algorithm based on Direct Robust MatrixFactorization (DRMF) is proven to be effective, requiring iteratively performing Singular Value Decomposition (SVD) for low rank matrix approximation would result in a prohibitively highaccumulated computation cost when the data matrix is large. In this work, we observe the quick false data location feature from our empirical study of DRMF, based on which we propose anintelligent Light weight Low Rank and False Matrix Separation algorithm (LightLRFMS) that can reuse the previous result of the matrix decomposition to deduce the one for the current iteration step. Our algorithm can largely speed up the whole iteration process.
