Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
 
(299 intermediate revisions by 7 users not shown)
Line 1: Line 1:
The reading list could be found [[Resource:Reading_List|here]].
{{SemNote
<pre style="white-space: pre-wrap;">
|time='''2024-11-1 10:30-12:00'''
Time:2020-11-18 14:30
|addr=4th Research Building A533
Address:主楼B-705-2 会议室
|note=Useful links: [[Resource:Reading_List|📚 Readling list]]; [[Resource:Seminar_schedules|📆 Schedules]]; [[Resource:Previous_Seminars|🧐 Previous seminars]].
</pre>
}}


===Latest===


=== Latest ===
{{Latest_seminar
{{Latest_seminar
|confname=IEEE Transactions on Mobile Computing
|abstract = Sparsely-activated Mixture-of-Expert (MoE) layers have found practical applications in enlarging the model size of large-scale foundation models, with only a sub-linear increase in computation demands. Despite the wide adoption of hybrid parallel paradigms like model parallelism, expert parallelism, and expert-sharding parallelism (i.e., MP+EP+ESP) to support MoE model training on GPU clusters, the training efficiency is hindered by communication costs introduced by these parallel paradigms. To address this limitation, we propose Parm, a system that accelerates MP+EP+ESP training by designing two dedicated schedules for placing communication tasks. The proposed schedules eliminate redundant computations and communications and enable overlaps between intra-node and inter-node communications, ultimately reducing the overall training time. As the two schedules are not mutually exclusive, we provide comprehensive theoretical analyses and derive an automatic and accurate solution to determine which schedule should be applied in different scenarios. Experimental results on an 8-GPU server and a 32-GPU cluster demonstrate that Parm outperforms the state-of-the-art MoE training system, DeepSpeed-MoE, achieving 1.13× to 5.77× speedup on 1296 manually configured MoE layers and approximately 3× improvement on two real-world MoE models based on BERT and GPT-2.
|link=https://ieeexplore.ieee.org/abstract/document/9078842/
|confname =INFOCOM‘24
|title=A Fuzzy Logic-based On-demand Charging Algorithm for Wireless Rechargeable Sensor Networks with Multiple Chargers
|link = https://ieeexplore.ieee.org/abstract/document/10621327
|speaker=Rong Cong
|title= Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules
|date=2020-11-19
|speaker=Mengqi
|date=2024-11-1
}}
}}
 
{{Latest_seminar
=== History ===
|abstract = HD map is a key enabling technology towards fully autonomous driving. We propose VI-Map, the first system that leverages roadside infrastructure to enhance real-time HD mapping for autonomous driving. The core concept of VI-Map is to exploit the unique cumulative observations made by roadside infrastructure to build and maintain an accurate and current HD map. This HD map is then fused with on-vehicle HD maps in real time, resulting in a more comprehensive and up-to-date HD map. By extracting concise bird-eye-view features from infrastructure observations and utilizing vectorized map representations, VI-Map incurs low compute and communication overhead. We conducted end-to-end evaluations of VI-Map on a real-world testbed and a simulator. Experiment results show that VI-Map can construct decentimeter-level (up to 0.3 m) HD maps and achieve real-time (up to a delay of 42 ms) map fusion between driving vehicles and roadside infrastructure. This represents a significant improvement of 2.8× and 3× in map accuracy and coverage compared to the state-of-the-art online HD mapping approaches. A video demo of VI-Map on our real-world testbed is available at https://youtu.be/p2RO65R5Ezg.
====2020====
|confname=Mobicom'23
{{Hist_seminar
|link = https://dl.acm.org/doi/abs/10.1145/3570361.3613280
|confname=Mobisys20
|title= VI-Map: Infrastructure-Assisted Real-Time HD Mapping for Autonomous Driving
|link=https://dl.acm.org/doi/10.1145/3386901.3388913
|speaker=Wangyang
|title=Combating packet collisions using non-stationary signal scaling in LPWANs
|date=2024-11-1
|speaker=Wenliang Mao
|date=2020-11-18
}}
 
{{Hist_seminar
|confname=Paper_Carnival_2020
|link=http://mobinets.org/index.php?title=Resource:Paper_Carnival_2019
|title=[[Resource:Paper_Carnival_2020|Paper Carnival 2020]]
|speaker=ALL
|date=2020-09-24,25,26
}}
 
{{Hist_seminar
|confname=INFOCOM'20
|link=https://infocom2020.ieee-infocom.org/accepted-paper-list-main-conference
|title=Optimizing Federated Learning on Non-IID Data with Reinforcement Learning
|speaker=YuHong Jiang
|date = 2020-5-16
}}
}}


{{Hist_seminar
{{Resource:Previous_Seminars}}
|confname=INFOCOM'20
|link=https://arxiv.org/pdf/2002.11850
|title=Joint Optimization of Signal Design and Resource Allocation in Wireless D2D Edge Computing
|speaker=Shiqi Hu
|date=2020-4-20
}}
{{Hist_seminar
|confname=INFOCOM'20
|link=https://www4.comp.polyu.edu.hk/~csyqzheng/papers/LiteNap-INFOCOM20.pdf
|title=LiteNap: Downclocking LoRa Reception
|speaker=Wenliang Mao
|date=2020-4-13
}}
{{Hist_seminar
|confname=INFOCOM'20
|link=https://arxiv.org/abs/2002.02596
|title=Delay-Optimal Distributed Edge Computing in Wireless Edge Networks
|speaker=Chang Shu
|date= 2020-3-30
}}
{{Hist_seminar
|confname=IoTJ 2018
|link=https://ieeexplore.ieee.org/document/8371243
|title=Over-the-Air Computation for IoT Networks: Computing Multiple Functions With Antenna Arrays
|speaker=Yuhong Jiang
|date=2020-3-23
}}
{{Hist_seminar
|confname=SIGCOMM'19
|link=https://dl.acm.org/doi/abs/10.1145/3341302.3342081
|title=RF-based Inertial Measurement
|speaker=Weifeng Gao
|date=2020-3-16
}}
====2019====
 
{{Hist_seminar
|confname=ICDCS'19
|link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/3i4wf2M7nD3nbkXbcbx1Do/5ZUGADKwrq6X0AzD4emr9c.pdf
|title=FRAME: Fault Tolerant and Real-Time Messaging for Edge Computing
|speaker=Xiaosong Wang
|date=2019-12-25
}}
{{Hist_seminar
|confname=INFOCOM'19
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8737456
|title=Intelligent Edge-Assisted Crowdcast with Deep Reinforcement Learning for Personalized QoE
|speaker=Hengwei Deng
|date=2019-12-25
}}
{{Hist_seminar
|confname=ieee communications magazine'18
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8466366
|title=Orchestration of Microservices for IoT Using Docker and Edge Computing
|speaker=Changsheng Liu
|date=2019-12-17
}}
{{Hist_seminar
|confname=Computer Science'13
|link=https://www.cs.toronto.edu/~vmnih/docs/dqn.pdf
|title=Playing Atari with Deep Reinforcement Learning
|speaker=Jie Zhang
|date=2019-12-17
}}
{{Hist_seminar
|confname=ICNP'19
|link=https://icnp19.cs.ucr.edu/proceedings/MainConference/FullPapers/icnp2019-final8.pdf
|title=Exploiting Rateless Codes and Cross-Layer Optimization for Low-Power Wide-Area Networks
|speaker=Silin Feng
|date=2019-11-13
}}
{{Hist_seminar
|confname=ICDCS'19
|link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/yzgM12TqeMYjWMqMhtP8N/7zRQAZeZ0fbS1oMqRXu5YR.pdf
|title=DMRA: A Decentralized Resource Allocation Scheme for Multi-SP Mobile Edge Computing
|speaker=Jiwei Mo
|date=2019-11-13
}}
{{Hist_seminar
|confname=MobiCom'19
|link=http://www.winlab.rutgers.edu/~luyang/papers/mobicom19_augmented_reality.pdf
|title=Edge Assisted Real-time Object Detection for MobileAugmented Reality
|speaker=Yunpeng Han
|date=2019-11-06
}}
{{Hist_seminar
|confname=NSDI'20
|link=http://mobinets.org/index.php?title=Resource:Seminar#
|title=Frequency Configuration for Low-Power Wide-Area Networks in a Heartbeat
|speaker=Xiong Wang
|date=2019-11-06
}}
{{Hist_seminar
|confname=MobiSys'16
|link=https://www.microsoft.com/en-us/research/publication/mobility-modeling-prediction-bike-sharing-systems-2/
|title=Mobility Modeling and Prediction in Bike-Sharing Systems
|speaker=Anqi Yang
|date=2019-10-30
}}
{{Hist_seminar
|confname=Tech. Rep.
|link=http://mobinets.org/index.php?title=Resource:Seminar#
|title=LoRa Localization
|speaker=Xuan Yang
|date=2019-10-30
}}
{{Hist_seminar
|confname=SigComm'19
|link=https://people.cs.uchicago.edu/~junchenj/docs/E2E_Sigcomm19.pdf
|title=E2E: Embracing User Heterogeneity to ImproveQuality of Experience on the Web
|speaker=Jingwei Li
|date=2019-10-23
}}
{{Hist_seminar
|confname=ICDCS'19
|link=https://www.cse.ust.hk/~weiwa/papers/cmfl-icdcs19.pdf
|title=CMFL: Mitigating Communication Overhead for Federated Learning
|speaker=Yuhong Jiang
|date=2019-10-23
}}
{{Hist_seminar
|confname=Tech.Rep.
|link=http://mobinets.org/index.php?title=Resource:Seminar#
|title=Report on LoRa reliable protocols
|speaker=Wenliang Mao
|date=2019-10-16
}}
{{Hist_seminar
|confname=ICDCS'19
|link=https://conferences.computer.org/icdcs/2019/pdfs/ICDCS2019-49XpIlu3rRtYi2T0qVYnNX/4s7uYmRKCj0LsGXo56pEeY/6q2XcJvusaWopfasaMSRAA.pdf
|title=Computation Offloading for Mobile-Edge Computing with Multi-user
|speaker=Chang Shu
|date=2019-10-16
}}
 
{{Hist_seminar
|confname=Paper_Carnival_2019
|link=http://mobinets.org/index.php?title=Resource:Paper_Carnival_2019
|title= [[Resource:Paper_Carnival_2019|Paper Carnival 2019]]
|speaker=ALL
|date=2019-09-28,29,30
}}
{{Hist_seminar
|confname=INFOCOM'19
|link=http://netarchlab.tsinghua.edu.cn/~junbi/INFOCOM2019-1.pdf
|title=Octans: Optimal Placement of Service Function Chains in Many-Core Systems
|speaker=Yuntong Zhang
|date=2019-05-22
}}
{{Hist_seminar
|confname=INFOCOM'19
|link=https://ieeexplore.ieee.org/abstract/document/8737660
|title=Adaptive Interference-Aware VNF Placement for Service-Customized 5G Network Slices
|speaker=Zhe Wang
|date=2019-05-22
}}
{{Hist_seminar
|confname=Tech. Rep.
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Recent progress and further trends on EdgeCloudSim
|speaker=Yunpeng Han
|date=2019-04-19
}}
{{Hist_seminar
|confname=MobiCom'19
|link=https://arxiv.org/pdf/1812.03103.pdf
|title=mD-Track: Leveraging Multi-Dimensionality for Passive Indoor Wi-Fi Tracking
|speaker=Xuan Yang
|date=2019-04-19
}}
{{Hist_seminar
|confname=NSDI'19
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Correctness and Performance for Stateful Chained Network Functions
|speaker=Yunpeng Han
|date=2019-04-19
}}
{{Hist_seminar
|confname=INFOCOM'19
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Charging Oriented Sensor Placement and Flexible Scheduling in Rechargeable WSN
|speaker=Wenjie Huang
|date=2019-04-12
}}
{{Hist_seminar
|confname=SIGCOMM'13
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Developing a Predictive Model of Quality of Experience for Internet Video
|speaker=Yuhong Jiang
|date=2019-04-12
}}
{{Hist_seminar
|confname=INFOCOM'19
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Brush like a Dentist: Accurate Monitoring of Toothbrushing via Wrist-Worn Gesture Sensing
|speaker=Jingwei Li
|date=2019-03-29
}}
{{Hist_seminar
|confname=INFOCOM'19
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Nomad: An Efficient Consensus Approach for Latency-Sensitive Edge-Cloud Applications
|speaker=Anqi Yang
|date=2019-03-29
}}
{{Hist_seminar
|confname=INFOCOM'19
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Winning at the Starting Line: Joint Network Selection and Service Placement for Mobile Edge Computing
|speaker=Chang Shu
|date=2019-03-22
}}
{{Hist_seminar
|confname=INFOCOM'19
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Interference Recycling: Exploiting Interfering Signals to Enhance Data Transmission
|speaker=Wenliang Mao
|date=2019-03-22
}}
{{Hist_seminar
|confname=COMST'18
|link=https://ieeexplore.ieee.org/document/8430735/
|title=Small Cells in the Forthcoming 5G/IoT: Traffic Modeling and Deployment Overview
|speaker=Anqi Yang
|date=2019-01-04
}}
 
====2018====
{{Hist_seminar
|confname=SIGCOMM'18
|link=https://conferences.sigcomm.org/events/apnet2018/papers/elastic_sketch.pdf
|title=Elastic Sketch: Adaptive and Fast Network-wide Measurements
|speaker=Wenliang Mao
|date=2018-12-21
}}
{{Hist_seminar
|confname=TMC'17
|link=https://ieeexplore.ieee.org/document/7458131/
|title=Performance analysis of mobile data offloading in heterogeneous networks
|speaker=Yunpeng Han
|date=2018-12-06
}}
{{Hist_seminar
|confname=COMST'18
|link=https://ieeexplore.ieee.org/document/8430735/
|title=Small Cells in the Forthcoming 5G/IoT: Traffic Modelling and Deployment Overview
|speaker=Anqi Yang
|date=2018-12-06
}}
{{Hist_seminar
|confname=TMC'17
|link=http://ieeexplore.ieee.org/document/7272098/
|title=A Reliability-Augmented Particle Filter for Magnetic Fingerprinting based Indoor Localization on Sma
|speaker=Wenjie Huang
|date=2018-11-30
}}
{{Hist_seminar
|confname=ToN'18
|link=https://ieeexplore.ieee.org/abstract/document/8519737
|title=A Distributed Computation Offloading Strategy in Small-Cell Networks Integrated With Mobile Edge Computing
|speaker=Yuhong Jiang
|date=2018-11-23
}}
{{Hist_seminar
|confname=ICNP'18
|link=https://ieeexplore.ieee.org/abstract/document/8526830
|title=Networking Support For Physical-Layer Cross-Technology Communication
|speaker=Jingwei Li
|date=2018-11-23
}}
{{Hist_seminar
|confname=IoT Journal'18
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8361406
|title=Mobile-Edge Computation Offloading for Ultra-Dense IoT Networks
|speaker=Chang Shu
|date=2018-11-16
}}
{{Hist_seminar
|confname=IPSN'17
|link=http://mpc.ece.utexas.edu/media/uploads/publishing/blend_ipsn17.pdf
|title=BLEnd: Practical Continuous Neighbor Discovery for Bluetooth Low Energy
|speaker=Minghang Yang
|date=2018-11-16
}}
{{Hist_seminar
|confname=Topic
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=LoRa Applications (two papers)
|speaker=Xinyuan Huang
|date=2018-10-19
}}
{{Hist_seminar
|confname=TMC'17
|link=https://ieeexplore.ieee.org/abstract/document/8476204
|title=Static and Mobile Target k-Coverage in Wireless Rechargeable Sensor Networks
|speaker=Shuowei Chen
|date=2018-10-19
}}
{{Hist_seminar
|confname=EWSN'17
|link=https://dl.acm.org/citation.cfm?id=3108015
|title=MOR: Multichannel Opportunistic Routing for Wireless Sensor Networks
|speaker=Xuan Yang
|date=2018-10-12
}}
{{Hist_seminar
|confname=TMC'17
|link=https://ieeexplore.ieee.org/abstract/document/7874147
|title= Hermes: Latency Optimal Task Assignment for Resource-constrained Mobile Computing
|speaker=Yunpeng Han
|date=2018-10-12
}}
{{Hist_seminar
|confname=MobiCom'17
|link=https://www.youtube.com/watch?v=e02p7813kN8
|title=FoggyCache: Cross-Device Approximate Computation Reuse
|speaker=Jingwei Li
|date=2018-09-30
}}
{{Hist_seminar
|confname=INFOCOM'18
|link=https://ieeexplore.ieee.org/abstract/document/8406950/
|title=Knowledge-centric proactive edge caching over mobile content distribution network
|speaker=Anqi Yang
|date=2018-09-21
}}
{{Hist_seminar
|confname=TWC'18
|link=https://ieeexplore.ieee.org/abstract/document/8443421/
|title=Enhancing Video Rate Adaptation with Mobile Edge Computing and Caching in Software-defined Mobile Ne
|speaker=Yuhong Jiang
|date=2018-09-21
}}
{{Hist_seminar
|confname=INFOCOM'18
|link=https://netlab.dcs.gla.ac.uk/uploads/files/4239e2a52ef02c46fbdccb8ad0de1448.pdf
|title=Dynamic,Latency-Optimal vNF Placement at the Network Edge
|speaker=Latency-Optimal vNF Placement at the Network Edge
|date=Chang Shu}}
{{Hist_seminar
|confname=TMC'17
|link=https://ieeexplore.ieee.org/abstract/document/7572937/
|title=Neighbor Discovery and Rendezvous Maintenance with Extended Quorum Systems for Mobile Applications
|speaker=Minghang Yang
|date=2018-09-14
}}
{{Hist_seminar
|confname=Special Session
|link=http://mobinets.org/seminar/carnival18mns/program.pdf
|title=3-day discussion on recent papers in wireless,networking and mobile
|speaker=networking and mobile</a>
|date=Chang Shu}}
{{Hist_seminar
|confname=IPSN'18
|link=https://dl.acm.org/citation.cfm?id=3207955
|title=Charm: Exploiting Geographical Diversity Through Coherent Combining in Low-Power Wide-Area Networks
|speaker=Weifeng Gao
|date=2018-06-15
}}
{{Hist_seminar
|confname=INFOCOM'18
|link=http://grid.hust.edu.cn/fmliu/vnf-scaling-infocom1
|title=Adaptive VNF Scaling and Flow Routing with Proactive Demand Prediction
|speaker=Chang Shu
|date=2018-06-15
}}
{{Hist_seminar
|confname=ComMag'17
|link=https://ieeexplore.ieee.org/document/8004165/
|title=The Algorithmic Aspects of Network Slicing
|speaker=Yunpeng Han
|date=2018-06-08
}}
{{Hist_seminar
|confname=IPSN'18
|link=https://dl.acm.org/citation.cfm?id=3207954
|title=Continuous Wireless Link Rates for Internet of Things
|speaker=Luqi Yang
|date=2018-06-08
}}
{{Hist_seminar
|confname=INFOCOM'18
|link=https://www.researchgate.net/publication/325190993
|title=TwinBee: Reliable Physical-Layer Cross-Technology Communication with Symbol-Level Coding
|speaker=Xinyuan Huang
|date=2018-06-01
}}
{{Hist_seminar
|confname=Invited Tech.Rep.
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Report on recent research progress
|speaker=Songfan Li
|date=2018-06-01
}}
{{Hist_seminar
|confname=Special Session
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=Scheduling Algorithms for Resource-Constrained Systems
|speaker=Prof. Dakai Zhu from UTSA
|date=2018-05-28
}}
{{Hist_seminar
|confname=CVPR'17
|link=https://ieeexplore.ieee.org/document/8099631/
|title=Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning
|speaker=Hui Cao
|date=2018-05-21
}}
{{Hist_seminar
|confname=INFOCOM'18
|link=http://people.umass.edu/hcai/
|title=Self-Adapting Quorum-Based Neighbor Discovery in Wireless Sensor Networks
|speaker=Minghang Yang
|date=2018-05-21
}}
{{Hist_seminar
|confname=Special Session
|link=http://mobinets.org/index.php?title=Resource:Seminar
|title=From Location to Activity: Human-centric Sensing and Analytics
|speaker=Prof. Tao Gu
|date=2018-05-11
}}
{{Hist_seminar
|confname=INFOCOM'18
|link=#
|title=LipPass: Lip Reading-based User Authentication on Smartphones Leveraging Acoustic Signals
|speaker=Shuowei Chen
|date=2018-04-27
}}
{{Hist_seminar
|confname=JSAC'17
|link=https://ieeexplore.ieee.org/document/8058433
|title=QoE-Aware and Reliable Traffic Steering for Service Function Chaining in Mobile Networks
|speaker=Zhe Wang
|date=2018-04-27
}}
{{Hist_seminar
|confname=JSAC'17
|link=http://rboutaba.cs.uwaterloo.ca/Papers/Journals/20
|title=Distributed Service Function Chaining
|speaker=Yuntong Zhang
|date=2018-04-13
}}
{{Hist_seminar
|confname=INFOCOM'18
|link=https://arxiv.org/pdf/1801.05868
|title=Joint Service Caching and Task Offloading for Mobile Edge Computing in Dense Networks
|speaker=Zi Wang
|date=2018-04-13
}}
{{Hist_seminar
|confname=INFOCOM'18
|link=https://arxiv.org/pdf/1712.06056.pdf
|title=One-Hop Out-of-Band Control Planes for Low-Power Multi-Hop Wireless Networks
|speaker=Chang Shu
|date=2018-03-16
}}
{{Hist_seminar
|confname=SigComm'16
|link=https://pdfs.semanticscholar.org/8e22/6c40a8c056dc
|title=OpenBox: A Software-De?ned Framework for Developing,Deploying,and Managing Network Functions
|speaker=Deploying
|date=and Managing Network Functions</a>}}
{{Hist_seminar
|confname=SigComm'17
|link=https://pdfs.semanticscholar.org/fa3b/9634b6057b3f
|title=Empowering Low-Power Wide Area Networks in Urban Settings
|speaker=Weifeng Gao
|date=2018-02-02
}}
{{Hist_seminar
|confname=ComMag16
|link=http://ieeexplore.ieee.org/abstract/document/81988
|title=Hypergraph Theory: Applications in 5G Heterogeneous Ultra-Dense Networks
|speaker=Yunpeng Han
|date=2018-01-26
}}
{{Hist_seminar
|confname=TCST'17
|link=http://ieeexplore.ieee.org/abstract/document/82372
|title=Optimal UAV Route Planning for Coverage Search of Stationary Target in River
|speaker=Hui Cao
|date=2018-01-26
}}
 
====2017====
 
{{Hist_seminar
|confname=MobiCom'17
|link=https://www.ntu.edu.sg/home/junluo/documents/Refle
|title=ReflexCode: Coding with Superposed Reflection Light for LED-Camera Communication
|speaker=Xinyuan Huang
|date=2017-12-08
}}
{{Hist_seminar
|confname=Proc. IEEE 2016
|link=http://ieeexplore.ieee.org/document/7423655/
|title=Using Smart Edge IoT Devices for Safer,Rapid Response With Industry IoT Control Operations
|speaker=Rapid Response With Industry IoT Control Operations</a>
|date=Minghang Yang}}
{{Hist_seminar
|confname=INFOCOM'17
|link=http://ieeexplore.ieee.org/document/8057039/
|title=Approximation Algorithms for The NFV Service Distribution Problem
|speaker=Yuntong Zhang
|date=2017-11-24
}}
{{Hist_seminar
|confname=CCS'17
|link=https://endchan.xyz/.media/50cf379143925a3926298f8
|title=DolphinAtack: Inaudible Voice Commands
|speaker=Zifei Zhao
|date=2017-11-24
}}
{{Hist_seminar
|confname=NSDI'17
|link=https://www.usenix.org/conference/nsdi17/technical
|title=Improving User Perceived Page Load Times Using Gaze
|speaker=Yaoyao Pang
|date=2017-11-17
}}
{{Hist_seminar
|confname=CoNEXT'16
|link=https://dl.acm.org/citation.cfm?id=2999602
|title=Flurries: Countless Fine-Grained NFs for Flexible Per-Flow Customization
|speaker=Zhe Wang
|date=2017-11-17
}}
{{Hist_seminar
|confname=MobiCom'17
|link=https://dl.acm.org/citation.cfm?id=3117843
|title=PassiveVLC: Enabling Practical Visible Light Backscatter Communication for Battery-free IoT Applicat
|speaker=Weifeng Gao
|date=2017-11-10
}}
{{Hist_seminar
|confname=INFOCOM'17
|link=http://ieeexplore.ieee.org/document/8057229/
|title=Service Chain Embedding with Maximum Flow in Software-defined Network and Application to The Next-Ge
|speaker=Chang Shu
|date=2017-11-10
}}
{{Hist_seminar
|confname=INFOCOM'17
|link=http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumbe
|title=BAC: Bandwidth-Aware Compression for EfficientLive Migration of Virtual Machines
|speaker=Yunpeng Han
|date=2017-11-03
}}
{{Hist_seminar
|confname=MobiCom'17
|link=https://dl.acm.org/ft_gateway.cfm?id=3117816&ftid=
|title=WEBee: Physical-Layer Cross-Technology Communication via Emulation
|speaker=Shuowei Chen
|date=2017-11-03
}}
{{Hist_seminar
|confname=SigComm'17
|link=http://conferences.sigcomm.org/sigcomm/2017/files/
|title=NFVnice: Dynamic Backpressure and Scheduling for NFV Service Chains
|speaker=Hui Cao
|date=2017-10-27
}}
{{Hist_seminar
|confname=MobiCom'17
|link=https://kabru.eecs.umich.edu/wordpress/wp-content/
|title=Continuous Authentication for Voice Assistants
|speaker=Heng Yuan
|date=2017-10-27
}}
{{Hist_seminar
|confname=TWC'17
|link=http://ieeexplore.ieee.org/document/7929399/
|title=Computation Offloading and Resource Allocation in Wireless Cellular Networks With Mobile Edge Computing
|speaker=Xinyuan Huang
|date=2017-10-20
}}
{{Hist_seminar
|confname=ToN'17
|link=http://ieeexplore.ieee.org/document/7784410/
|title=Chase: Taming concurrent broadcast for flooding in asynchronous duty cycle networks
|speaker=Minghang Yang
|date=2017-10-20
}}
{{Hist_seminar
|confname=TOSN'17
|link=http://www.comp.nus.edu.sg/~mobashir/Resources/Pap
|title=Improving Performance of Synchronous Transmission-Based Protocols Using Capture Effect over Multicha
|speaker=Luqi Yang
|date=2017-10-13
}}
{{Hist_seminar
|confname=SigComm'17
|link=http://conferences.sigcomm.org/sigcomm/2017/files/
|title=Dynamic Service Chaining with Dysco
|speaker=Chang Shu
|date=2017-10-13
}}
{{Hist_seminar
|confname=INFOCOM'17
|link=http://personal.stevens.edu/~ychen6/papers/ER%20Ea
|title=ER: Early Recognition of Inattentive Driving Leveraging Audio Devices on Smartphones
|speaker=Zifei Zhao
|date=2017-09-29
}}
{{Hist_seminar
|confname=INFOCOM'17
|link=https://thawproject.files.wordpress.com/2017/04/li
|title=LightTouch: Securely Connecting Wearables to Ambient Displays with User Intent
|speaker=Yaoyao Pang
|date=2017-09-22
}}
{{Hist_seminar
|confname=INFOCOM'17
|link=https://users.cs.fiu.edu/~pand/publications/17info
|title=Traffic Aware Placement of Interdependent NFV Middleboxes
|speaker=Zhe Wang
|date=2017-09-22
}}
{{Hist_seminar
|confname=SigComm'17
|link=https://people.cs.clemson.edu/~hongxih/papers/SIGC
|title=NFP: Enabling Network Function Parallelism in NFV
|speaker=Yuntong Zhang
|date=2017-09-22
}}
{{Hist_seminar
|confname=NFV-SDN'16
|link=https://www.net.t-labs.tu-berlin.de/~stefan/o4sdi1
|title=Efficient service Graph Embedding: A Practical Approach
|speaker=Chang Shu
|date=2017-09-11
}}
{{Hist_seminar
|confname=SenSys'17
|link=http://www.simonduquennoy.net
|title=Network-wide Consensus Utilizing the Capture Effect in Low-power Wireless Networks
|speaker=Weifeng Gao
|date=2017-09-11
}}
{{Hist_seminar
|confname=INFOCOM'17
|link=https://arxiv.org/abs/1612.06507
|title=Survivable and Bandwidth Guaranteed Embe
|speaker=Yuntong Zhang
|date=2017-06-26
}}
{{Hist_seminar
|confname=MobiCom'15
|link=
|title=Survivable and Bandwidth Guaranteed Embedding of Virtual Clusters in Cloud Data Centers
|speaker=Yuntong Zhang
|date=2017-06-26
}}
{{Hist_seminar
|confname=MobiCom'15
|link=https://www.sigmobile.org/mobicom/2015/papers/p9
|title=Keystroke Recognition Using WiFi Signals
|speaker=Weiwang Li
|date=2017-06-26
}}
 
===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history部分
# 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
 
*格式说明
** Latest_seminar:
<blockquote><small>
{{Latest_seminar
<br>|confname=
<br>|link=
<br>|title=
<br>|speaker=
<br>}}
</small>
</blockquote>
** Hist_seminar
<blockquote><small>
{{Hist_seminar
<br>|confname=
<br>|link=
<br>|title=
<br>|speaker=
<br>|date=
<br>}}
</small></blockquote>

Latest revision as of 05:48, 1 November 2024

Time: 2024-11-1 10:30-12:00
Address: 4th Research Building A533
Useful links: 📚 Readling list; 📆 Schedules; 🧐 Previous seminars.

Latest

  1. [INFOCOM‘24] Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules, Mengqi
    Abstract: Sparsely-activated Mixture-of-Expert (MoE) layers have found practical applications in enlarging the model size of large-scale foundation models, with only a sub-linear increase in computation demands. Despite the wide adoption of hybrid parallel paradigms like model parallelism, expert parallelism, and expert-sharding parallelism (i.e., MP+EP+ESP) to support MoE model training on GPU clusters, the training efficiency is hindered by communication costs introduced by these parallel paradigms. To address this limitation, we propose Parm, a system that accelerates MP+EP+ESP training by designing two dedicated schedules for placing communication tasks. The proposed schedules eliminate redundant computations and communications and enable overlaps between intra-node and inter-node communications, ultimately reducing the overall training time. As the two schedules are not mutually exclusive, we provide comprehensive theoretical analyses and derive an automatic and accurate solution to determine which schedule should be applied in different scenarios. Experimental results on an 8-GPU server and a 32-GPU cluster demonstrate that Parm outperforms the state-of-the-art MoE training system, DeepSpeed-MoE, achieving 1.13× to 5.77× speedup on 1296 manually configured MoE layers and approximately 3× improvement on two real-world MoE models based on BERT and GPT-2.
  2. [Mobicom'23] VI-Map: Infrastructure-Assisted Real-Time HD Mapping for Autonomous Driving, Wangyang
    Abstract: HD map is a key enabling technology towards fully autonomous driving. We propose VI-Map, the first system that leverages roadside infrastructure to enhance real-time HD mapping for autonomous driving. The core concept of VI-Map is to exploit the unique cumulative observations made by roadside infrastructure to build and maintain an accurate and current HD map. This HD map is then fused with on-vehicle HD maps in real time, resulting in a more comprehensive and up-to-date HD map. By extracting concise bird-eye-view features from infrastructure observations and utilizing vectorized map representations, VI-Map incurs low compute and communication overhead. We conducted end-to-end evaluations of VI-Map on a real-world testbed and a simulator. Experiment results show that VI-Map can construct decentimeter-level (up to 0.3 m) HD maps and achieve real-time (up to a delay of 42 ms) map fusion between driving vehicles and roadside infrastructure. This represents a significant improvement of 2.8× and 3× in map accuracy and coverage compared to the state-of-the-art online HD mapping approaches. A video demo of VI-Map on our real-world testbed is available at https://youtu.be/p2RO65R5Ezg.

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

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
    • 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=
}}