Advanced topics in mobile and social computing (AToMSC) (Summer 2021)

From NET Wiki
Revision as of 21:07, 13 April 2021 by Yuan4 (talk | contribs) (→‎Schedule)
Jump to navigation Jump to search

Details

Workload/ECTS Credits: 5 ECTS
Module: M.Inf.1222.Mp: Specialization Computer Networks Module Description -or- 3.10: Advanced Topics in Internet Research (II)(ITIS); M.Inf.1223 (new Regulations)
Lecturer: Prof. Xiaoming Fu; Dr. Tingting Yuan
Teaching assistant: [NA]
Time: Thu. 14:00-16:00
Place: IfI 0.101
UniVZ [1]


Announcements

Due to the recent recommendations in the context of Covid-19, this course is scheduled to be held online. We plan to use some tools and platforms, e.g., zoom or DFNconf. Please register into studIP in advance. The registration deadline is at 23:59 pm on 11th April 2021. I will announce which tool will be used before our lectures start. Please contact me by email:adhatarao@cs.uni-goettingen.de if you have any questions.

Course Overview

The purpose of this seminar is to discuss some advanced topics in computer networks. This course is a theory-oriented research seminar (5 ECTS, 2 SWS), held on a weekly base and comprises the following components:

  • Weekly Presentation + Weekly Paper Reading and Discussion 40%
  • Final Presentation 25%
  • Final Report 35%

The material in the seminar is mainly drawn from the research literature in top journals/conferences, like ToN,TMC, TPDS, SIGCOMM, SIGMETRICS, INFOCOM, MOBICOM, MOBIHOC, WWW, CoNEXT.

Requirements

  • Each participant is required to read the assigned paper before the seminar and prepare the review of the paper, which should include the following parts:
    • Summary of the paper
    • Pros and cons of the paper (your conclusion)
    • NOTE!! Every participant should provide the paper review BEFORE the seminar (23:59 Wednesday). => the review form is available at [Paper_Review_Form_ATCN_WS201112.doc]
  • During each weekly seminar, two participants are assigned for presenting the paper (each presentation lasts for ~20 minutes) and the list of pros and cons are discussed by all the participants.
  • In the middle of the semester, everyone is requested to pick a topic and prepare:
    • Final report: Essay (5~6 pages, double columns, IEEE format) for your chosen research topic, which contains a comprehensive literature survey + a detailed discussion of some key enabling technologies
    • Final presentation: each presentation lasts for ~20 minutes, plus ~10 minutes Q&A

List of Papers

  • 1. Video streaming in NN-based system
    • (1) Neural Adaptive Content-aware Internet Video Delivery [2] OSDI'18
    • (2) Neural-Enhanced Live Streaming: Improving Live Video Ingest via Online Learning [3] Sigcomm'20
    • (3) NEMO: Enabling Neural-enhanced Video Streaming on Commodity Mobile Devices [4] Mobicom'20
  • 2. Network for Distributed Learning
    • (1) Is Network the Bottleneck of Distributed Training? [5] Sigcomm workshop 20
    • (2) Domain-specific Communication Optimization for Distributed DNN Training [6] arxiv
    • (3) PipeDream: generalized pipeline parallelism for DNN training[7] SOSP ’19
  • 3. Network Control
    • (1) Neural Packet Routing [8] Sigcomm workshop 20
    • (2) OmniMon: Re-architecting Network Telemetry with Resource Efficiency and Full Accuracy [9] Sigcomm 20
    • (3) Swift: Delay is Simple and Effective for Congestion Control in the Datacenter[10] Sigcomm 20
  • 4. AI for Network I
    • (1) SmartEntry: Mitigating Routing Update Overhead with Reinforcement Learning for Traffic Engineering [11] Sigcomm workshop 20
    • (2) Event-Triggered Communication Network with Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning [12] AAAI 21
    • (3) Learning Scheduling Algorithms for Data Processing Clusters [13] Sigcomm 19
  • 5. AI for Network II
    • (1) SmartEntry: Mitigating Routing Update Overhead with Reinforcement Learning for Traffic Engineering [14] Sigcomm workshop 20
    • (2) Interpreting Deep Learning-Based Networking Systems [15]Sigcomm 20
    • (3) PCF: Provably Resilient Flexible Routing [16] Sigcomm 20

Schedule

  • 15 April 2021
    • Informational Meeting
  • 22 April 2021
    • No lecture (Girls Day)
  • 29 April 2021
    • Paper Title: Neural Adaptive Content-aware Internet Video Delivery
  • 06 May 2021
    • Paper Title: Is Network the Bottleneck of Distributed Training?
  • 13 May 2021
    • No lecture (Ascension Day)
  • 20 May 2021
    • Paper Title: Neural Packet Routing
  • 27 May 2021
    • Paper Title: SmartEntry: Mitigating Routing Update Overhead with Reinforcement Learning for Traffic Engineering
  • 03 June 2021
    • Paper Title: SmartEntry: Mitigating Routing Update Overhead with Reinforcement Learning for Traffic Engineering
  • 10 June 2021
    • Paper Title: Neural-Enhanced Live Streaming: Improving Live Video Ingest via Online Learning
  • 17 June 2021
    • Paper Title: Domain-specific Communication Optimization for Distributed DNN Training
  • 24 June 2021
    • Paper Title: OmniMon: Re-architecting Network Telemetry with Resource Efficiency and Full Accuracy
  • 01 July 2021
    • Paper Title: Event-Triggered Communication Network with Limited-Bandwidth Constraint for Multi-Agent Reinforcement Learning
  • 09 July 2021
    • Paper Title: Interpreting Deep Learning-Based Networking Systems
  • 16 July 2021 (Final slides submission)
    • Paper Title: NEMO: Enabling Neural-enhanced Video Streaming on Commodity Mobile Devices
    • Paper Title: PipeDream: generalized pipeline parallelism for DNN training
    • Paper Title: Swift: Delay is Simple and Effective for Congestion Control in the Datacenter
    • Paper Title: Learning Scheduling Algorithms for Data Processing Clusters
    • Paper Title:

Final Presentations & Report

  • Final Registration in FlexNow: July 1st 2021.


  • Final Presentation:
    • Each for ~20 minutes, plus ~10 minutes Q&A


  • Final Presentation Slots:
    • To Be Announced (TBA)