Advanced Topics in AI for Computing and Networking (Winter 2024/2025): Difference between revisions
(Created page with "== Details == {{CourseDetails |credits=5 ECTS |module=M.Inf.1123 |lecturer=[http://134.76.18.81/?q=people/prof-dr-xiaoming-fu Prof. Xiaoming Fu]; [http://www.net.informatik.uni-goettingen.de/?q=people/dr-tingting-yuan, Dr. Tingting Yuan]; Wenfang Wu; |ta=[NA] |time=Thursday 14:00-16:00 |place= }} ==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...") |
|||
(One intermediate revision by the same user not shown) | |||
Line 32: | Line 32: | ||
==List of Papers == | ==List of Papers == | ||
1. | 1. NetLLM: Adapting Large Language Models for Networking [https://doi.org/10.1145/3651890.3672268] | ||
2. | 2. m3: Accurate Flow-Level Performance Estimation using Machine Learning [https://doi.org/10.1145/3651890.3672243] | ||
3. | 3. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving [https://doi.org/10.1145/3651890.3672274] | ||
4. | 4. Crux: GPU-Efficient Communication Scheduling for Deep Learning Training [https://doi.org/10.1145/3651890.3672239] | ||
5. | 5. Dissecting Carrier Aggregation in 5G Networks: Measurement, QoE Implications and Prediction [https://doi.org/10.1145/3651890.3672250] | ||
6. | 6. Transferable Neural WAN TE for Changing Topologies [https://dl.acm.org/doi/10.1145/3570361.3613299] | ||
7. | 7. RDMA over Ethernet for Distributed Training at Meta Scale [https://doi.org/10.1145/3651890.3672233] | ||
8. | 8. RedTE: Mitigating Subsecond Traffic Bursts with Real-time and Distributed Traffic Engineering [https://doi.org/10.1145/3651890.3672231] | ||
9. | 9. TopFull: An Adaptive Top-Down Overload Control for SLO-Oriented Microservices [https://doi.org/10.1145/3651890.3672253] | ||
10. | 10. Smart Data-Driven Proactive Push to Edge Network [https://doi.org/10.1109/INFOCOM52122.2024.10621410] | ||
11. | 11. A Generic Blockchain-based Steganography Framework with High Capacity via Reversible GAN [https://doi.org/10.1109/INFOCOM52122.2024.10621377] | ||
12. | 12. Det-RAN: Data-Driven Cross-Layer Real-Time Attack Detection in 5G Open RANs [https://doi.org/10.1109/INFOCOM52122.2024.10621223] | ||
13. | 13. TITANIC: Towards Production Federated Learning with Large Language Models [https://doi.org/10.1109/INFOCOM52122.2024.10621164] | ||
14. | 14. Tomtit: Hierarchical Federated Fine-Tuning of Giant Models based on Autonomous Synchronization [https://doi.org/10.1109/INFOCOM52122.2024.10621369] | ||
15. | 15. Predicting Multi-Scale Information Diffusion via Minimal Substitution Neural Networks [https://doi.org/10.1109/INFOCOM52122.2024.10621418] | ||
16. | 16. Practical Adversarial Attack on WiFi Sensing Through Unnoticeable Communication Packet Perturbation [https://doi.org/10.1145/3636534.3649367] | ||
17. A | 17. Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving [https://doi.org/10.1145/3636534.3649352] | ||
18. | 18. AutoDroid: LLM-powered Task Automation in Android [https://doi.org/10.1145/3636534.3649379] | ||
19. | 19. FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices [https://doi.org/10.1145/3636534.3649391] | ||
20. | 20. Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices [https://doi.org/10.1145/3636534.3649363] | ||
==Schedule== | ==Schedule== | ||
W1: Open Talk (11 | W1: Open Talk (02.11) | ||
W2: Select papers and create schedule | W2: Select papers and create schedule | ||
Line 91: | Line 91: | ||
'''!! xx.xx deadline for registration on Flexnow''' | '''!! xx.xx deadline for registration on Flexnow''' | ||
Final Presentation (xx. | Final Presentation (xx.01) | ||
*'''Paper Title''': | *'''Paper Title''': | ||
*'''Paper Title''': | *'''Paper Title''': | ||
Line 112: | Line 112: | ||
*Final Report: | *Final Report: | ||
**Essay (~6 pages, double column, IEEE format: https://journals.ieeeauthorcenter.ieee.org/create-your-ieee-journal-article/authoring-tools-and-templates/ieee-article-templates/templates-for-transactions/) | **Essay (~6 pages, double column, IEEE format: https://journals.ieeeauthorcenter.ieee.org/create-your-ieee-journal-article/authoring-tools-and-templates/ieee-article-templates/templates-for-transactions/) | ||
**Due by 23:59pm 15th | **Due by 23:59pm 15th February. | ||
[[Category:Courses]] | [[Category:Courses]] |
Latest revision as of 13:18, 14 October 2024
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 40%
- Final Report 20%
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. NetLLM: Adapting Large Language Models for Networking [1]
2. m3: Accurate Flow-Level Performance Estimation using Machine Learning [2]
3. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving [3]
4. Crux: GPU-Efficient Communication Scheduling for Deep Learning Training [4]
5. Dissecting Carrier Aggregation in 5G Networks: Measurement, QoE Implications and Prediction [5]
6. Transferable Neural WAN TE for Changing Topologies [6]
7. RDMA over Ethernet for Distributed Training at Meta Scale [7]
8. RedTE: Mitigating Subsecond Traffic Bursts with Real-time and Distributed Traffic Engineering [8]
9. TopFull: An Adaptive Top-Down Overload Control for SLO-Oriented Microservices [9]
10. Smart Data-Driven Proactive Push to Edge Network [10]
11. A Generic Blockchain-based Steganography Framework with High Capacity via Reversible GAN [11]
12. Det-RAN: Data-Driven Cross-Layer Real-Time Attack Detection in 5G Open RANs [12]
13. TITANIC: Towards Production Federated Learning with Large Language Models [13]
14. Tomtit: Hierarchical Federated Fine-Tuning of Giant Models based on Autonomous Synchronization [14]
15. Predicting Multi-Scale Information Diffusion via Minimal Substitution Neural Networks [15]
16. Practical Adversarial Attack on WiFi Sensing Through Unnoticeable Communication Packet Perturbation [16]
17. Soar: Design and Deployment of A Smart Roadside Infrastructure System for Autonomous Driving [17]
18. AutoDroid: LLM-powered Task Automation in Android [18]
19. FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices [19]
20. Asteroid: Resource-Efficient Hybrid Pipeline Parallelism for Collaborative DNN Training on Heterogeneous Edge Devices [20]
Schedule
W1: Open Talk (02.11)
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 ~20 minutes Q&A
- Final Presentation Slots:
- To Be Announced (TBA)
- Final Report:
- Essay (~6 pages, double column, IEEE format: https://journals.ieeeauthorcenter.ieee.org/create-your-ieee-journal-article/authoring-tools-and-templates/ieee-article-templates/templates-for-transactions/)
- Due by 23:59pm 15th February.