Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
(368 intermediate revisions by 12 users not shown)
Line 1: Line 1:
=== Latest ===
{{SemNote
- ''The '''INFOCOM 2020 Cycle''' starts from June 1st and ends at August 1st, during which the seminar is temporarily suspended.''
|time='''Friday 10:30-12:00'''
<pre style="white-space: pre-wrap;">
|addr=4th Research Building A518
Time:2019-05-10
|note=Useful links: [[Resource:Reading_List|Readling list]]; [[Resource:Seminar_schedules|Schedules]]; [[Resource:Previous_Seminars|Previous seminars]].
Address:B1-612, Main Building, Qingshuihe, UESTC
}}
</pre>
<!--
***根据说明修改此页***
USAGE:  
1. copy the code in the latest seminar and paste them in the history section.
2. Replace the {{Latest_seminar... as {{Hist_seminar
3. Place the code for the latest seminars. Format:
    {{Latest_seminar|Conference/journal name|download link|Paper title|Speaker}}
    e.g., {{Latest_seminar|INFOCOM'19|http://|A paper|San Zhang}}
-->


{{Latest_seminar|INFOCOM'19|http://netarchlab.tsinghua.edu.cn/~junbi/INFOCOM2019-1.pdf|Octans: Optimal Placement of Service Function Chains in Many-Core Systems|Yuntong Zhang}}
===Latest===
{{Latest_seminar|INFOCOM'19|https://ieeexplore.ieee.org/abstract/document/8737660|Adaptive Interference-Aware VNF Placement for Service-Customized 5G Network Slices|Zhe Wang}}
{{Latest_seminar
=== History ===
|abstract=Continual learning (CL) trains NN models incrementally from a continuous stream of tasks. To remember previously learned knowledge, prior studies store old samples over a memory hierarchy and replay them when new tasks arrive. Edge devices that adopt CL to preserve data privacy are typically energy-sensitive and thus require high model accuracy while not compromising energy efficiency, i.e., cost-effectiveness. Our work is the first to explore the design space of hierarchical memory replay-based CL to gain insights into achieving cost-effectiveness on edge devices. We present Miro, a novel system runtime that carefully integrates our insights into the CL framework by enabling it to dynamically configure the CL system based on resource states for the best cost-effectiveness. To reach this goal, Miro also performs online profiling on parameters with clear accuracy-energy trade-offs and adapts to optimal values with low overhead. Extensive evaluations show that Miro significantly outperforms baseline systems we build for comparison, consistently achieving higher cost-effectiveness.
{{Hist_seminar|Tech. Rep.||Recent progress and further trends on EdgeCloudSim|Yunpeng Han}}
|confname=MobiCom'23
* [Tech. Rep.] Recent progress and further trends on EdgeCloudSim, Yunpeng Han, 2019-04-19
|link=https://arxiv.org/pdf/2308.06053
* [MobiCom'19] mD-Track: Leveraging Multi-Dimensionality for Passive Indoor Wi-Fi Tracking, Xuan Yang, 2019-04-19
|title=Cost-effective On-device Continual Learning over Memory Hierarchy with Miro
* [NSDI'19 ] Correctness and Performance for Stateful Chained Network Functions, Yunpeng Han, 2019-04-19
|speaker=Jiale
* [INFOCOM'19] Charging Oriented Sensor Placement and Flexible Scheduling in Rechargeable WSN, Wenjie Huang, 2019-04-12
|date=2024-06-14}}
* [SIGCOMM'13] Developing a Predictive Model of Quality of Experience for Internet Video, Yuhong Jiang, 2019-04-12
{{Latest_seminar
* [INFOCOM'19] Brush like a Dentist: Accurate Monitoring of Toothbrushing via Wrist-Worn Gesture Sensing, Jingwei Li, 2019-03-29
|abstract=Multi-view 3D reconstruction driven augmented, virtual, and mixed reality applications are becoming increasingly edge-native, due to factors such as, rapid reconstruction needs, security/privacy concerns, and lack of connectivity to cloud platforms. Managing edge-native 3D reconstruction, due to edge resource constraints and inherent dynamism of ‘in the wild’ 3D environments, involves striking a balance between conflicting objectives of achieving rapid reconstruction and satisfying minimum quality requirements. In this paper, we take a deeper dive into multi-view 3D reconstruction latency-quality trade-off, with an emphasis on reconstruction of dynamic 3D scenes. We propose data-level and task-level parallelization of 3D reconstruction pipelines, holistic edge system optimizations to reduce reconstruction latency, and long-term minimum reconstruction quality satisfaction. The proposed solutions are validated through collection of real-world 3D scenes with varying degree of dynamism that are used to perform experiments on hardware edge testbed. The results show that our solutions can achieve between 50% to 75% latency reduction without violating long term minimum quality requirements.
* [INFOCOM'19] Nomad: An Efficient Consensus Approach for Latency-Sensitive Edge-Cloud Applications, Anqi Yang, 2019-03-29
|confname=SEC'23
* [INFOCOM'19] Winning at the Starting Line: Joint Network Selection and Service Placement for Mobile Edge Computin, Chang Shu, 2019-03-22
|link=https://www.cs.hunter.cuny.edu/~sdebroy/publication-files/SEC2023_CR.pdf
* [INFOCOM'19] Interference Recycling: Exploiting Interfering Signals to Enhance Data Transmission, Wenliang Mao, 2019-03-22
|title=On Balancing Latency and Quality of Edge-Native Multi-View 3D Reconstruction
* [COMST'18] Small Cells in the Forthcoming 5G/IoT: Traffic Modeling and Deployment Overview, Anqi Yang, 2019-01-04
|speaker=Yang Wang
* [SIGCOMM'18] Elastic Sketch: Adaptive and Fast Network-wide Measurements, Wenliang Mao, 2018-12-21
|date=2024-06-14}}
* [TMC'17] Performance analysis of mobile data offloading in heterogeneous networks, Yunpeng Han, 2018-12-06
{{Resource:Previous_Seminars}}
* [COMST'18] Small Cells in the Forthcoming 5G/IoT: Traffic Modelling and Deployment Overview, Anqi Yang, 2018-12-06
* [TMC'17] A Reliability-Augmented Particle Filter for Magnetic Fingerprinting based Indoor Localization on Sma, Wenjie Huang, 2018-11-30
* [ToN'18] A Distributed Computation Offloading Strategy in Small-Cell Networks Integrated With Mobile Edge Com, Yuhong Jiang, 2018-11-23
* [ICNP'18] Networking Support For Physical-Layer Cross-Technology Communication, Jingwei Li, 2018-11-23
* [IoT Journal'18] Mobile-Edge Computation Offloading for Ultra-Dense IoT Networks, Chang Shu, 2018-11-16
* [IPSN'17] BLEnd: Practical Continuous Neighbor Discovery for Bluetooth Low Energy, Minghang Yang, 2018-11-16
* [Topic] LoRa Applications (two papers), Xinyuan Huang, 2018-10-19
* [TMC'17] Static and Mobile Target k-Coverage in Wireless Rechargeable Sensor Networks, Shuowei Chen, 2018-10-19
* [EWSN'17] MOR: Multichannel Opportunistic Routing for Wireless Sensor Networks, Xuan Yang, 2018-10-12
* [TMC'17] Hermes: Latency Optimal Task Assignment for Resource-constrained Mobile Computing, Yunpeng Han, 2018-10-12
* [MobiCom'17] FoggyCache: Cross-Device Approximate Computation Reuse, Jingwei Li, 2018-09-30
* [INFOCOM'18] Knowledge-centric proactive edge caching over mobile content distribution network, Anqi Yang, 2018-09-21
* [TWC'18] Enhancing Video Rate Adaptation with Mobile Edge Computing and Caching in Software-defined Mobile Ne, Yuhong Jiang, 2018-09-21
* [INFOCOM'18] Dynamic, Latency-Optimal vNF Placement at the Network Edge, Chang Shu, 2018-09-14
* [TMC'17] Neighbor Discovery and Rendezvous Maintenance with Extended Quorum Systems for Mobile Applications, Minghang Yang, 2018-09-14
* [Special Session] 3-day discussion on recent papers in wireless, networking and mobile, Chang Shu, Weifeng Gao, etc., 2018-08-29
* [IPSN'18] Charm: Exploiting Geographical Diversity Through Coherent Combining in Low-Power Wide-Area Networks, Weifeng Gao, 2018-06-15
* [INFOCOM'18] Adaptive VNF Scaling and Flow Routing with Proactive Demand Prediction, Chang Shu, 2018-06-15
* [ComMag'17] The Algorithmic Aspects of Network Slicing, Yunpeng Han, 2018-06-08
* [IPSN'18] Continuous Wireless Link Rates for Internet of Things, Luqi Yang, 2018-06-08
* [INFOCOM'18] TwinBee: Reliable Physical-Layer Cross-Technology Communication with Symbol-Level Coding, Xinyuan Huang, 2018-06-01
* [Invited Tech.Rep.] Report on recent research progress, Songfan Li, 2018-06-01
* [Special Session] Scheduling Algorithms for Resource-Constrained Systems, Prof. Dakai Zhu from UTSA, 2018-05-28
* [CVPR'17] Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning, Hui Cao, 2018-05-21
* [INFOCOM'18] Self-Adapting Quorum-Based Neighbor Discovery in Wireless Sensor Networks, Minghang Yang, 2018-05-21
* [Special Session] From Location to Activity: Human-centric Sensing and Analytics, Prof. Tao Gu, 2018-05-11
* [INFOCOM'18] LipPass: Lip Reading-based User Authentication on Smartphones Leveraging Acoustic Signals, Shuowei Chen, 2018-04-27
* [JSAC'17] QoE-Aware and Reliable Traffic Steering for Service Function Chaining in Mobile Networks, Zhe Wang, 2018-04-27
* [JSAC'17] Distributed Service Function Chaining, Yuntong Zhang, 2018-04-13
* [INFOCOM'18] Joint Service Caching and Task Offloading for Mobile Edge Computing in Dense Networks, Zi Wang, 2018-04-13
* [INFOCOM'18] One-Hop Out-of-Band Control Planes for Low-Power Multi-Hop Wireless Networks, Chang Shu, 2018-03-16
* [SigComm'16] OpenBox: A Software-De?ned Framework for Developing, Deploying, and Managing Network Functions, Chang Shu, 2018-02-02
* [SigComm'17] Empowering Low-Power Wide Area Networks in Urban Settings, Weifeng Gao, 2018-02-02
* [ComMag16] Hypergraph Theory: Applications in 5G Heterogeneous Ultra-Dense Networks, Yunpeng Han, 2018-01-26
* [TCST'17] Optimal UAV Route Planning for Coverage Search of Stationary Target in River, Hui Cao, 2018-01-26
* [MobiCom'17] ReflexCode: Coding with Superposed Reflection Light for LED-Camera Communication, Xinyuan Huang, 2017-12-08
* [Proc. IEEE 2016] Using Smart Edge IoT Devices for Safer, Rapid Response With Industry IoT Control Operations, Minghang Yang, 2017-12-08
* [INFOCOM'17] Approximation Algorithms for The NFV Service Distribution Problem, Yuntong Zhang, 2017-11-24
* [CCS'17] DolphinAtack: Inaudible Voice Commands, Zifei Zhao, 2017-11-24
* [NSDI'17] Improving User Perceived Page Load Times Using Gaze, Yaoyao Pang, 2017-11-17
* [CoNEXT'16] Flurries: Countless Fine-Grained NFs for Flexible Per-Flow Customization, Zhe Wang, 2017-11-17
* [MobiCom'17] PassiveVLC: Enabling Practical Visible Light Backscatter Communication for Battery-free IoT Applicat, Weifeng Gao, 2017-11-10
* [INFOCOM'17] Service Chain Embedding with Maximum Flow in Software-defined Network and Application to The Next-Ge, Chang Shu, 2017-11-10
* [INFOCOM'17] BAC: Bandwidth-Aware Compression for EfficientLive Migration of Virtual Machines, Yunpeng Han, 2017-11-03
* [MobiCom'17] WEBee: Physical-Layer Cross-Technology Communication via Emulation, Shuowei Chen, 2017-11-03
* [SigComm'17] NFVnice: Dynamic Backpressure and Scheduling for NFV Service Chains, Hui Cao, 2017-10-27
* [MobiCom'17] Continuous Authentication for Voice Assistants, Heng Yuan, 2017-10-27
* [TWC'17] Computation Offloading and Resource Allocation in Wireless Cellular Networks With Mobile Edge Comput, Xinyuan Huang, 2017-10-20
* [ToN'17] Chase: Taming concurrent broadcast for flooding in asynchronous duty cycle networks, Minghang Yang, 2017-10-20
* [TOSN'17] Improving Performance of Synchronous Transmission-Based Protocols Using Capture Effect over Multicha, Luqi Yang, 2017-10-13
* [SigComm'17] Dynamic Service Chaining with Dysco, Chang Shu, 2017-10-13
* [INFOCOM'17] ER: Early Recognition of Inattentive Driving Leveraging Audio Devices on Smartphones, Zifei Zhao, 2017-09-29
* [INFOCOM'17] LightTouch: Securely Connecting Wearables to Ambient Displays with User Intent, Yaoyao Pang, 2017-09-22
* [INFOCOM'17] Traffic Aware Placement of Interdependent NFV Middleboxes, Zhe Wang, 2017-09-22
* [SigComm'17] NFP: Enabling Network Function Parallelism in NFV, Yuntong Zhang, 2017-09-22
* [NFV-SDN'16] Efficient service Graph Embedding: A Practical Approach, Chang Shu, 2017-09-11
* [SenSys'17] Network-wide Consensus Utilizing the Capture Effect in Low-power Wireless Networks, Weifeng Gao, 2017-09-11
* [INFOCOM'17] Survivable and Bandwidth Guaranteed Embe, Yuntong Zhang, 2017-06-26
* [MobiCom'15] Survivable and Bandwidth Guaranteed Embedding of Virtual Clusters in Cloud Data Centers, Yuntong Zhang, 2017-06-26
* [MobiCom'15] Keystroke Recognition Using WiFi Signals, Weiwang Li, 2017-06-26

Revision as of 15:22, 11 June 2024

Time: Friday 10:30-12:00
Address: 4th Research Building A518
Useful links: Readling list; Schedules; Previous seminars.

Latest

  1. [MobiCom'23] Cost-effective On-device Continual Learning over Memory Hierarchy with Miro, Jiale
    Abstract: Continual learning (CL) trains NN models incrementally from a continuous stream of tasks. To remember previously learned knowledge, prior studies store old samples over a memory hierarchy and replay them when new tasks arrive. Edge devices that adopt CL to preserve data privacy are typically energy-sensitive and thus require high model accuracy while not compromising energy efficiency, i.e., cost-effectiveness. Our work is the first to explore the design space of hierarchical memory replay-based CL to gain insights into achieving cost-effectiveness on edge devices. We present Miro, a novel system runtime that carefully integrates our insights into the CL framework by enabling it to dynamically configure the CL system based on resource states for the best cost-effectiveness. To reach this goal, Miro also performs online profiling on parameters with clear accuracy-energy trade-offs and adapts to optimal values with low overhead. Extensive evaluations show that Miro significantly outperforms baseline systems we build for comparison, consistently achieving higher cost-effectiveness.
  2. [SEC'23] On Balancing Latency and Quality of Edge-Native Multi-View 3D Reconstruction, Yang Wang
    Abstract: Multi-view 3D reconstruction driven augmented, virtual, and mixed reality applications are becoming increasingly edge-native, due to factors such as, rapid reconstruction needs, security/privacy concerns, and lack of connectivity to cloud platforms. Managing edge-native 3D reconstruction, due to edge resource constraints and inherent dynamism of ‘in the wild’ 3D environments, involves striking a balance between conflicting objectives of achieving rapid reconstruction and satisfying minimum quality requirements. In this paper, we take a deeper dive into multi-view 3D reconstruction latency-quality trade-off, with an emphasis on reconstruction of dynamic 3D scenes. We propose data-level and task-level parallelization of 3D reconstruction pipelines, holistic edge system optimizations to reduce reconstruction latency, and long-term minimum reconstruction quality satisfaction. The proposed solutions are validated through collection of real-world 3D scenes with varying degree of dynamism that are used to perform experiments on hardware edge testbed. The results show that our solutions can achieve between 50% to 75% latency reduction without violating long term minimum quality requirements.

History

2024

2023

2022

2021

2020

  • [Topic] [ The path planning algorithm for multiple mobile edge servers in EdgeGO], Rong Cong, 2020-11-18

2019

2018

2017

Template loop detected: Resource:Previous Seminars

Instructions

请使用Latest_seminar和Hist_seminar模板更新本页信息.

    • 修改时间和地点信息
    • 将当前latest seminar部分的code复制到这个页面中
    • 将{{Latest_seminar... 修改为 {{Hist_seminar...，并增加对应的日期信息|date=
    • 填入latest seminar各字段信息
    • link请务必不要留空，如果没有link则填本页地址 https://mobinets.org/index.php?title=Resource:Seminar
  • 格式说明
    • Latest_seminar:

{{Latest_seminar
|confname=
|link=
|title=
|speaker=
}}

    • Hist_seminar

{{Hist_seminar
|confname=
|link=
|title=
|speaker=
|date=
}}

Retrieved from "http://mobinets.cn/site/index.php?title=Resource:Seminar&oldid=2842"