https://cis.temple.edu/~jiewu/research/publications/Publication_files/Paper%206190%20Camera%20Ready%20Version.pdf
a major challenge for federated learning in diverse settings. Personalized Federated Learning (PFL), [Tan et al., 2022a] addresses these issues by allowing client-specific models that leverage global insights to enhance local outcomes. The main challenge in PFL lies in balancing global knowledge sharing with preserving client-specific information, making the trade- off an important research ...
https://sites.temple.edu/bjsewall/files/2021/08/Freestone-et-al-2021-Ecology-Stronger-predation-intensity-impact-on-prey-communities-in-the-tropics.pdf
Test-ing the prediction that both predation intensity and im-pacts on prey communities are greater at lower latitudes requires standardized experiments and observations on multiple components of a system across continental scales.
https://cis.temple.edu/~wu/research/publications/Publication_files/jsan-13-00044-v2.pdf
Abstract: Harnessing remote computation power over the Internet without the need for expensive hardware and making costly services available to mass users at a marginal cost gave birth to the concept of cloud computing. This survey provides a concise overview of the growing confluence of cloud computing, edge intelligence, and AI, with a focus on their revolutionary impact on the Internet of ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/Reinforcement_Learning-based_Dual-Identity_Double_Auction_in_Personalized_Federated_Learning.pdf
Reinforcement Learning-based Dual-Identity Auction in Personalized Federated Juan Li, Member, IEEE, Zishang Chen, Tianzi Wu, Fellow, IEEE, Yanmin
https://www.fox.temple.edu/sites/fox/files/documents/CVs/xueming-luo-cv.pdf
Bio: Xueming Luo is the Charles Gilliland Distinguished Chair Professor of Marketing, Professor of Strategy, and Professor of MIS, and Founder/ Director of the Global Institute for Artificial Intelligence & Business Analytics in the Fox School of Business at Temple University. He is an interdisciplinary thought-leader in leveraging AI/ML algorithms, text/audio/image/video big data ...
https://cis.temple.edu/~wu/research/publications/Publication_files/1571039973-LCN2024.pdf
Abstract—Local Area Networks (LANs), as interconnected networks, are susceptible to numerous security threats. Existing intrusion detection systems (IDS) heavily rely on large, fully-labeled datasets to have accurate detection, facing challenges when only a few malicious samples are available. In addition, previous studies have identified the deterioration of IDS’s per-formance when the ...
https://cis.temple.edu/~wu/teaching/Spring%202013/handoff.pdf
1.1 INTRODUCTION Mobility is the most important feature of a wireless cellular communication system. Usu-ally, continuous service is achieved by supporting handoff (or handover) from one cell to another. Handoff is the process of changing the channel (frequency, time slot, spreading code, or combination of them) associated with the current connection while a call is in progress. It is often ...
https://sites.temple.edu/xifanwu/files/2020/10/PhysRevLett.125.156803.pdf
We report a joint study using surface-specific sum-frequency vibrational spectroscopy and ab initio molecular dynamics simulations, respectively, on a pristine hydrophobic (sub)monolayer hexane-water interface, namely, the hexane/water interface with varied vapor pressures of hexane and different pHs in water. We show clear evidence that hexane on water revises the interfacial water structure ...
https://cis.temple.edu/~wu/research/publications/Publication_files/Joint%20Dynamic%20Grouping%20and%20Gradient%20Coding%20for%20Time-critical%20Distributed%20Machine%20Learning%20in%20Heterogeneous%20Edge%20Networks-FINAL-VERSION.pdf
Abstract—In edge networks, distributed computing resources have been widely utilized to collaboratively perform a machine learning task by multiple nodes. However, the model training time in heterogeneous edge networks is becoming longer because of excessive computation and delay caused by slow nodes, namely stragglers. The parameter server even abandons stragglers which fail to return ...
https://cis.temple.edu/~jiewu/research/publications/Publication_files/jiang_www_2020.pdf
ABSTRACT Serendipity recommendation has attracted more and more atten-tion in recent years; it is committed to providing recommendations which could not only cater to users’ demands but also broaden their horizons. However, existing approaches usually measure user-item relevance with a scalar instead of a vector, ignoring user preference direction, which increases the risk of unrelated ...