时间：2021.6.11下午2.30

地点：理科楼B311

标题：《Lightweight Feedback Convolution Neural Network for Remote Sensing ImagesSuper-Resolution》

汇报人：吴一鸣

摘要：

There are lots of image data in the eld of remote sensing, most of which have low-resolutiondue to the limited image sensor. The super-resolution method can effectively restore the low-resolutionimage to the high-resolution image. However, the existing super-resolution method has both heavy computingburden and number of parameters. For saving costs, we propose the feedback ghost residual densenetwork (FGRDN), which considers the feedback mechanism as the framework to attain lower featuresthrough high-level rening. Further, for feature extraction, we replace the convolution of the residual denseblocks (RDBs) with ghost modules (GMs), which can remove the redundant channels and avoid the increaseof parameters along with the network depth. Finally, the spatial and channel attention module (SCM) isemployed in the end of the RDB to learn more useful information from features. Compared to other SOTAlightweight algorithms, our proposed algorithm can reach convergences more rapidly with fewer parameters,and the performance of the network can be markedly enhanced on the image texture and object contourreconstruction with better peak signal-to-noise ratio (PSNR) and structural similarity (SSIM).

录取期刊：ACCESS

标题：《Multiple Strategies Differential Privacy on SparseTensor Factorization for Network Traffic Analysisin 5G》

汇报人：韩惠

摘要：

Due to high capacity and fast transmission speed, 5Gplays a key role in modern electronic infrastructure. Meanwhile,Sparse Tensor Factorization (STF) is a useful tool for dimension

reduction to analyze High-Order, High-Dimension, and SparseTensor (HOHDST) data which is transmitted on 5G Internetof-things (IoT). Hence, HOHDST data relies on STF to obtaincomplete data and discover rules for real-time and accurateanalysis. From another view of computation and data security,the current STF solution seeks to improve the computationalefficiency but neglects privacy security of the IoT data, e.g., dataanalysis for network traffic monitor system. To overcome theseproblems, this paper proposes a Multiple-strategies DifferentialPrivacy framework on STF (MDPSTF) for HOHDST networktraffic data analysis. MDPSTF comprises three Differential Privacy(DP) mechanisms, i.e., "DP, Concentrated DP (CDP), andLocal DP (LDP). Furthermore, the theoretical proof of privacybound is presented. Hence, MDPSTF can provide general dataprotection for HOHDST network traffic data with high-securitypromise. We conduct experiments on two real network trafficdatasets (Abilene and GEANT). The experimental results showthat MDPSTF has high universality on the various degrees ofprivacy protection demands and high recovery accuracy for theHOHDST network traffic data.

录取期刊：Transactions on Industrial Informatics

标题：《Deep Field-Aware Interaction Machine for Click-Through Rate Prediction》

汇报人：齐高峰

摘要：

Modeling feature interactions is of crucial importance to predict click-through rate (CTR) in industrial recommender systems.Because of great performance and efficiency, the factorization machine (FM) has been a popular approach to learn featureinteraction. Recently, several variants of FM are proposed to improve its performance, and they have proven the field informationto play an important role. However, feature-length in a field is usually small; we observe that when there are multiple nonzerofeatures within a field, the interaction between fields is not enough to represent the feature interaction between different fields due

to the problem of short feature-length. In this work, we propose a novel neural CTR model named DeepFIM by introducing FieldawareInteraction Machine (FIM), which provides a layered structure form to describe intrafield and interfield feature interaction,to solve the short-expression problem caused by the short feature-length in the field. Experiments show that our model achievescomparable and even materially better results than the state-of-the-art methods..

录取期刊：Mobile Information Systems