Advanced Topics in AI for Networking (Winter 2023/2024): Difference between revisions

From NET Wiki
Jump to navigation Jump to search
Line 32: Line 32:


==List of Papers ==
==List of Papers ==
1. Cosmo: Contrastive Fusion Learning with Small Data for Multimodal Human Activity Recognition [https://dl.acm.org/doi/pdf/10.1145/3495243.3560519]
1. FedAdapter: Efficient Federated Learning for Modern NLP [https://arxiv.org/pdf/2205.10162.pdf]


2. Learning for Crowdsourcing: Online Dispatch for Video Analytics with Guarantee [https://ieeexplore.ieee.org/document/9796960]  
2. AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving [https://dl.acm.org/doi/10.1145/3570361.3592517]


3. CASVA: Configuration-Adaptive Streaming for Live Video Analytics [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796875]
3. mmFER: Millimetre-wave Radar based Facial Expression Recognition for Multimedia IoT Applications [https://dl.acm.org/doi/10.1145/3570361.3592515]


4. Batch Adaptative Streaming for Video Analytics [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796853]
4. NeRF2: Neural Radio-Frequency Radiance Fields [https://dl.acm.org/doi/10.1145/3570361.3592527]


5. FlexPatch: Fast and Accurate Object Detection for On-device High-Resolution Live Video Analytics [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796984]
5. Exploiting Contactless Side Channels in Wireless Charging Power Banks for User Privacy Inference via Few-shot Learning [https://dl.acm.org/doi/10.1145/3570361.3613288]


6. AoI-minimal UAV Crowdsensing by Model-based Graph Convolutional Reinforcement Learning [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796732]
6. Practically Adopting Human Activity Recognition [https://dl.acm.org/doi/10.1145/3570361.3613299]


7. RouteNet-Erlang: A Graph Neural Network for Network Performance Evaluation [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796944]
7. Cosmo: Contrastive Fusion Learning with Small Data for Multimodal Human Activity Recognition [https://dl.acm.org/doi/pdf/10.1145/3495243.3560519]


8. Deep Reinforcement Learning-Based Control Framework for Radio Access Networks [https://dl.acm.org/doi/pdf/10.1145/3495243.3558276?casa_token=IlUioU8GgjwAAAAA:ygqCMlQv28WBdO-z65UXYjJIoeVoyEiwVI00D5nw_cNW0N6aHZCEdBzqt5r2A8jGT7pYuU8xJMJGIrs]
8. Learning for Crowdsourcing: Online Dispatch for Video Analytics with Guarantee [https://ieeexplore.ieee.org/document/9796960]  


9. NeuLens: Spatial-based Dynamic Acceleration of Convolutional Neural Networks on Edge [https://dl.acm.org/doi/pdf/10.1145/3495243.3560528?casa_token=mrLc2kitFkcAAAAA:lKf6MnXcwXxhr0SrODcIX7qP7DrthKc_yp7jZ-2MYoxmnutM4lHPuYXD5DrLrBjS38S15TbVwPSD-NA]
9. CASVA: Configuration-Adaptive Streaming for Live Video Analytics [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796875]


10. FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796926]
10. Batch Adaptative Streaming for Video Analytics [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796853]


11. TrojanFlow: A Neural Backdoor Attack to Deep Learning-based Network Traffic Classifiers [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796878]
11. FlexPatch: Fast and Accurate Object Detection for On-device High-Resolution Live Video Analytics [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796984]


12. Mousika: Enable General In-Network Intelligence in Programmable Switches by Knowledge Distillation [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796936]
12. AoI-minimal UAV Crowdsensing by Model-based Graph Convolutional Reinforcement Learning [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796732]


13. Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers [https://www.usenix.org/conference/nsdi22/presentation/bhardwaj]
13. RouteNet-Erlang: A Graph Neural Network for Network Performance Evaluation [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796944]


14. Top-K Deep Video Analytics: A Probabilistic Approach [https://dl.acm.org/doi/pdf/10.1145/3448016.3452786]
14. Deep Reinforcement Learning-Based Control Framework for Radio Access Networks [https://dl.acm.org/doi/pdf/10.1145/3495243.3558276?casa_token=IlUioU8GgjwAAAAA:ygqCMlQv28WBdO-z65UXYjJIoeVoyEiwVI00D5nw_cNW0N6aHZCEdBzqt5r2A8jGT7pYuU8xJMJGIrs]


15. Delay-Aware Microservice Coordination in Mobile Edge Computing: A Reinforcement Learning Approach [https://ieeexplore.ieee.org/document/8924682]
15. NeuLens: Spatial-based Dynamic Acceleration of Convolutional Neural Networks on Edge [https://dl.acm.org/doi/pdf/10.1145/3495243.3560528?casa_token=mrLc2kitFkcAAAAA:lKf6MnXcwXxhr0SrODcIX7qP7DrthKc_yp7jZ-2MYoxmnutM4lHPuYXD5DrLrBjS38S15TbVwPSD-NA]


16. Dynamic Scheduling for Stochastic Edge-Cloud Computing Environments Using A3C Learning and Residual Recurrent Neural Networks [https://ieeexplore.ieee.org/document/9169832]
16. FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796926]


17. Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computing [https://ieeexplore.ieee.org/document/9492755]
17. TrojanFlow: A Neural Backdoor Attack to Deep Learning-based Network Traffic Classifiers [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796878]


18. Leveraging Deep Reinforcement Learning With Attention Mechanism for Virtual Network Function Placement and Routing [https://ieeexplore.ieee.org/document/10029903]
18. Mousika: Enable General In-Network Intelligence in Programmable Switches by Knowledge Distillation [https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9796936]


19. Pyramid: Enabling Hierarchical Neural Networks with Edge Computing [https://dl.acm.org/doi/10.1145/3485447.3511990]
19. Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers [https://www.usenix.org/conference/nsdi22/presentation/bhardwaj]


20. Index-aware reinforcement learning for adaptive video streaming at the wireless edge [https://dl.acm.org/doi/10.1145/3492866.3549726]
20. Top-K Deep Video Analytics: A Probabilistic Approach [https://dl.acm.org/doi/pdf/10.1145/3448016.3452786]


==Schedule==
==Schedule==

Revision as of 23:10, 15 October 2023

Details

Workload/ECTS Credits: 5 ECTS
Module: M.Inf.1123
Lecturer: Prof. Xiaoming Fu; Dr. Tingting Yuan; Wenfang Wu;
Teaching assistant: [NA]
Time: Thursday 14:00-16:00


Announcements

Please contact me by email: wenfang.wu@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 30%
  • Final Report 30%

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 on Wedesday). => the review form is available at [Paper_Review_Form_ATCN_WS201112.doc]
  • During each weekly seminar, one participant is 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 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. FedAdapter: Efficient Federated Learning for Modern NLP [1]

2. AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving [2]

3. mmFER: Millimetre-wave Radar based Facial Expression Recognition for Multimedia IoT Applications [3]

4. NeRF2: Neural Radio-Frequency Radiance Fields [4]

5. Exploiting Contactless Side Channels in Wireless Charging Power Banks for User Privacy Inference via Few-shot Learning [5]

6. Practically Adopting Human Activity Recognition [6]

7. Cosmo: Contrastive Fusion Learning with Small Data for Multimodal Human Activity Recognition [7]

8. Learning for Crowdsourcing: Online Dispatch for Video Analytics with Guarantee [8]

9. CASVA: Configuration-Adaptive Streaming for Live Video Analytics [9]

10. Batch Adaptative Streaming for Video Analytics [10]

11. FlexPatch: Fast and Accurate Object Detection for On-device High-Resolution Live Video Analytics [11]

12. AoI-minimal UAV Crowdsensing by Model-based Graph Convolutional Reinforcement Learning [12]

13. RouteNet-Erlang: A Graph Neural Network for Network Performance Evaluation [13]

14. Deep Reinforcement Learning-Based Control Framework for Radio Access Networks [14]

15. NeuLens: Spatial-based Dynamic Acceleration of Convolutional Neural Networks on Edge [15]

16. FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning [16]

17. TrojanFlow: A Neural Backdoor Attack to Deep Learning-based Network Traffic Classifiers [17]

18. Mousika: Enable General In-Network Intelligence in Programmable Switches by Knowledge Distillation [18]

19. Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers [19]

20. Top-K Deep Video Analytics: A Probabilistic Approach [20]

Schedule

W1: Open Talk (26.10)

W2: Select papers and create schedule

W4: Paper ID:

W6: ...

W8: ...

W10: ...

W12: ...

W14: ..

!! xx.xx deadline for registration on Flexnow

Final Presentation (xx.01)

  • Paper Title:
  • Paper Title:

Report deadline

Final Presentations & Report

  • Final Registration in FlexNow: To Be Announced (TBA).


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


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


Retrieved from "https://wiki.net.informatik.uni-goettingen.de/index.php?title=Advanced_Topics_in_AI_for_Networking_(Winter_2023/2024)&oldid=8247"