Difference between revisions of "Resource:Seminar"

From MobiNetS
Jump to: navigation, search
m (wenliang updates seminars)
 
(141 intermediate revisions by 5 users not shown)
Line 1: Line 1:
{{SemNote
{{SemNote
|time='''2021-12-24 9:00'''
|time='''2024-03-22 10:30-12:00'''
|addr=Main Building B1-612
|addr=4th Research Building A518
|note=Useful links: [[Resource:Reading_List|Readling list]]; [[Resource:Seminar_schedules|Schedules]]; [[Resource:Previous_Seminars|Previous seminars]].
|note=Useful links: [[Resource:Reading_List|Readling list]]; [[Resource:Seminar_schedules|Schedules]]; [[Resource:Previous_Seminars|Previous seminars]].
}}
}}
Line 7: Line 7:
===Latest===
===Latest===
{{Latest_seminar
{{Latest_seminar
|abstract = Object detection is a fundamental building block of video analytics applications. While Neural Networks (NNs)-based object detection models have shown excellent accuracy on benchmark datasets, they are not well positioned for high-resolution images inference on resource-constrained edge devices. Common approaches, including down-sampling inputs and scaling up neural networks, fall short of adapting to video content changes and various latency requirements. This paper presents Remix, a flexible framework for high-resolution object detection on edge devices. Remix takes as input a latency budget, and come up with an image partition and model execution plan which runs off-the-shelf neural networks on non-uniformly partitioned image blocks. As a result, it maximizes the overall detection accuracy by allocating various amount of compute power onto different areas of an image. We evaluate Remix on public dataset as well as real-world videos collected by ourselves. Experimental results show that Remix can either improve the detection accuracy by 18%-120% for a given latency budget, or achieve up to 8.1× inference speedup with accuracy on par with the state-of-the-art NNs.
|abstract=Satellite routers in emerging space-terrestrial integrated networks (STINs) are operated in a failure-prone, intermittent and resource-constrained space environment, making it very critical but challenging to cope with various network failures effectively. Existing resilient routing approaches either suffer from continuous re-convergences with low network reachability, or involve prohibitive pre-computation and storage overhead due to the huge amount of possible failure scenarios in STINs.This paper presents StarCure, a novel resilient routing mechanism for futuristic STINs. StarCure aims at achieving fast and efficient routing restoration, while maintaining the low-latency, high-bandwidth service capabilities in failure-prone space environments. First, StarCure incorporates a new network model, called the topology-stabilizing model (TSM) to eliminate topological uncertainty by converting the topology variations caused by various failures to traffic variations. Second, StarCure adopts an adaptive hybrid routing scheme, collaboratively combining a constraint optimizer to efficiently handle predictable failures, together with a location-guided protection routing strategy to quickly deal with unexpected failures. Extensive evaluations driven by realistic constellation information show that, StarCure can protect routing against various failures, achieving close-to-100% reachability and better performance restoration with acceptable system overhead, as compared to other existing resilience solutions.
|confname= MobiCom 2021
|confname=INFOCOM 2023
|link=https://dl.acm.org/doi/abs/10.1145/3447993.3483274
|link=https://ieeexplore.ieee.org/document/10229104
|title=Flexible high-resolution object detection on edge devices with tunable latency
|title=Achieving Resilient and Performance-Guaranteed Routing in Space-Terrestrial Integrated Networks
|speaker=Rong
|speaker=Luwei
}}
|date=2024-03-29}}
{{Latest_seminar
{{Latest_seminar
|abstract = Deep Neural Networks (DNNs) have become an essential and important supporting technology for smart Internet-of-Things (IoT) systems. Due to the high computational costs of large-scale DNNs, it might be infeasible to directly deploy them in energy-constrained IoT devices. Through offloading computation-intensive tasks to the cloud or edges, the computation offloading technology offers a feasible solution to execute DNNs. However, energy-efficient offloading for DNN based smart IoT systems with deadline constraints in the cloud-edge environments is still an open challenge. To address this challenge, we first design a new system energy consumption model, which takes into account the runtime, switching, and computing energy consumption of all participating servers (from both the cloud and edge) and IoT devices. Next, a novel energy-efficient offloading strategy based on a Self-adaptive Particle Swarm Optimization algorithm using the Genetic Algorithm operators (SPSO-GA) is proposed. This new strategy can efficiently make offloading decisions for DNN layers with layer partition operations, which can lessen the encoding dimension and improve the execution time of SPSO-GA. Simulation results demonstrate that the proposed strategy can significantly reduce energy consumption compared to other classic methods.
|abstract=We propose a Communication-aware Pruning (CaP) algorithm, a novel distributed inference framework for distributing DNN computations across a physical network. Departing from conventional pruning methods, CaP takes the physical network topology into consideration and produces DNNs that are communication-aware, designed for both accurate and fast execution over such a distributed deployment. Our experiments on CIFAR-10 and CIFAR-100, two deep learning benchmark datasets, show that CaP beats state of the art competitors by up to 4% w.r.t. accuracy on benchmarks. On experiments over real-world scenarios, it simultaneously reduces total execution time by 27%–68% at negligible performance decrease (less than 1%).
|confname= TPDS 2022
|confname=INFOCOM 2023
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9497712
|link=https://ieeexplore.ieee.org/document/10229043
|title=Energy-Efficient Offloading for DNN-Based Smart IoT Systems in Cloud-Edge Environments
|title=Communication-aware DNN pruning
|speaker=Wenjie
|speaker=Shuhong
}}
|date=2024-03-29}}
{{Latest_seminar
|abstract = Data collection with mobile elements can improve energy efficiency and balance load distribution in wireless sensor networks (WSNs). However, complex network environments bring about inconvenience of path design. This work addresses the network environment issue, by presenting an objective-variable tour planning (OVTP) strategy for mobile data gathering in partitioned WSNs. Unlike existing studies of connected networks, our work focuses on disjoint networks with connectivity requirement and serves delay-hash applications as well as energy-efficient scenarios respectively. We first design a converging-aware location selection mechanism, which macroscopically converges rendezvous points (RPs) to lay a foundation of a short tour. We then develop a delay-aware path formation mechanism, which constructs a short tour connecting all segments by a new convex hull algorithm and a new genetic operation. In addition, we devise an energy-aware path extension mechanism, which selects appropriate extra RPs according to specific metrics in order to reduce the energy depletion of data transmission. Extensive simulations demonstrate the effectiveness and advantages of the new strategy in terms of path length, energy depletion, and data collection ratio.
|confname= TMC 2022
|link=https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9119834
|title=Objective-Variable Tour Planning for Mobile Data Collection in Partitioned Sensor Networks
|speaker=Zhuoliu
}}
 
=== History ===
{{Resource:Previous_Seminars}}
{{Resource:Previous_Seminars}}

Latest revision as of 14:03, 26 March 2024

Time: 2024-03-22 10:30-12:00
Address: 4th Research Building A518
Useful links: Readling list; Schedules; Previous seminars.

Latest

  1. [INFOCOM 2023] Achieving Resilient and Performance-Guaranteed Routing in Space-Terrestrial Integrated Networks, Luwei
    Abstract: Satellite routers in emerging space-terrestrial integrated networks (STINs) are operated in a failure-prone, intermittent and resource-constrained space environment, making it very critical but challenging to cope with various network failures effectively. Existing resilient routing approaches either suffer from continuous re-convergences with low network reachability, or involve prohibitive pre-computation and storage overhead due to the huge amount of possible failure scenarios in STINs.This paper presents StarCure, a novel resilient routing mechanism for futuristic STINs. StarCure aims at achieving fast and efficient routing restoration, while maintaining the low-latency, high-bandwidth service capabilities in failure-prone space environments. First, StarCure incorporates a new network model, called the topology-stabilizing model (TSM) to eliminate topological uncertainty by converting the topology variations caused by various failures to traffic variations. Second, StarCure adopts an adaptive hybrid routing scheme, collaboratively combining a constraint optimizer to efficiently handle predictable failures, together with a location-guided protection routing strategy to quickly deal with unexpected failures. Extensive evaluations driven by realistic constellation information show that, StarCure can protect routing against various failures, achieving close-to-100% reachability and better performance restoration with acceptable system overhead, as compared to other existing resilience solutions.
  2. [INFOCOM 2023] Communication-aware DNN pruning, Shuhong
    Abstract: We propose a Communication-aware Pruning (CaP) algorithm, a novel distributed inference framework for distributing DNN computations across a physical network. Departing from conventional pruning methods, CaP takes the physical network topology into consideration and produces DNNs that are communication-aware, designed for both accurate and fast execution over such a distributed deployment. Our experiments on CIFAR-10 and CIFAR-100, two deep learning benchmark datasets, show that CaP beats state of the art competitors by up to 4% w.r.t. accuracy on benchmarks. On experiments over real-world scenarios, it simultaneously reduces total execution time by 27%–68% at negligible performance decrease (less than 1%).

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
    • 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=
}}