- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes a new method for personalized decentralized federated learning under quantization. The authors propose a new method that combines existing methods on quantization and consensus and obtain a set of convergence analysis.
Critical strengths
- The paper targets a valid problem (i.e., quantized decentralized FL).
- Overall the paper is easy to read, although there is room for improvement (I will explain in my comments below).
Critical weaknesses
The paper suffers from a verity of issues that deserve careful considerations:
-
The paper claims tries to sell the convergence analysis more ambitious as what it really is. For example, in the abstract, it is mentioned that "We theoretically prove that Q-pFedMe converges linearly to a quantization-dependent neighborhood of the optimal solution for strongly convex objectives, and has an O(1/R) optimization term with an explicit error floor for smooth non-convex objectives." This claims, especially, the part for strongly convex case, is highly standard in decentralized FL literature. In particular, any decentralized FL method with inexact local solver or consensus (caused by quantization noise in this paper) will exhibit the same convergence behavior. Thus, it is not clear what is the main advantage of the proposed method, or what is the uniqueness of the analysis (in terms of the tightness of the bounds, etc.).
-
Line 77: It is not clear what does FP32 mean.
-
Line 111: The set notation (i.e., { }) is missed in both definitions of N^_ and N^+.
-
Eq. (7), as L approaches the value of \lambda, the value of the bound reaches infinity. This is questionable as the smoothness value (especially its smaller values) should not cause such extreme conditions.
-
The same issue arises in line 278: The denominator \lambda^2-8L^2, can be 0 or even negative when the only condition applied is \lambda> L in (7). This issue brings the entire results under question as the value of the fraction is presumed to be strictly positive in the convergence analysis (the left hand side is denoted by \sigma^2 to denote its positive nature).
-
In line 329, q_i^r is not clearly defined.
-
The bounds in Theorem 3 are questionable. Specifically, they are "upper bounds" on T. That means that for any value of T holding in those bounds, the claim of the Theorem, which is "reach exact agreement on the quantized average" should hold. Yet, T=0, 1, .... all hold in the bound. That means that the algorithm reaches perfect agreement even for T=0, 1, .... which does not seem to be correct.
-
The experimental section seems to be quite weak: 8-1) A variety of baselines on decentralized quantized FL, decentralized FL with sparsification, and event-triggered decentralized FL are missed. 8-2) The comparison to centralized FL can be moved to appendix to have more space for comparison to other decentralized FL methods. 8-3) The superiority of the algorithm should be compared with all the above methods under a variety of graph topologies (e.g., Scale-Free Graphs, Caveman Graphs, etc.) with varying connectivity level for the underlying graph topology. 8-4) The experiments above should be conducted under a wider level of data heterogeneity ranges (Dirichelet parameter ranging from 10^-3 to 10^3). This will show whether the advantage of the method is under extreme data heterogeneity or under homogeneous data across clients.
Questions for authors
Please refer to the comments above. In particular,
-
How the claims of the paper (mentioned in the first weakness comment) can be justified?
-
How the extreme values of conditions under varying values of L can be justified?
-
How to avoid having negative values of the condition mentioned in line 278 and how the proof changes under negative values?
-
How to justify the small values of T that hold in Theorem 3?
-
What is the reason behind limited simulations?