Summary of Learning the Optimal Path and Dnn Partition For Collaborative Edge Inference, by Yin Huang et al.
Learning the Optimal Path and DNN Partition for Collaborative Edge Inference
by Yin Huang, Letian Zhang, Jie Xu
First submitted to arxiv on: 2 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper tackles a crucial challenge in collaborative edge inference on mobile devices with unknown network parameters and multiple paths. To address this, the authors propose a novel approach that learns to select the optimal network path and assign DNN layers to nodes considering security threats and switching costs. The learning problem is formulated as an adversarial group linear bandits problem, which is solved using a new algorithm called B-EXPUCB. This algorithm combines elements of blocked EXP3 and LinUCB algorithms, achieving sublinear regret in simulations. The paper’s contributions include deriving structural insights from the DNN layer assignment with complete network information and introducing the B-EXPUCB algorithm for collaborative edge inference. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper solves a big problem in making smart mobile devices work well together. When many devices are connected, it can be hard to figure out which path data should take through the network. The authors came up with a new way to learn how to make these decisions based on unknown information and potential security threats. Their approach uses an algorithm called B-EXPUCB, which is better at making good choices than previous methods. This breakthrough has important implications for the development of intelligent mobile applications. |
Keywords
» Artificial intelligence » Inference
