Official Review · ICLR 2025

This paper is a direct extension based on DiffusionNAG, which can deal with multi-objective optimization in NAS. These objectives include accuracy, the number of parameters, multiply-accumulate operations (MACs), and inference latency. This motivation is good and natural, and the authors expressed their work clearly, from the motivation to the experiments results. Some details need to be clarified. This paper introduces the ParetoOptimal Many-Objective Neural Architecture Generator (POMONAG), extending DiffusionNAG through a many-objective diffusion process. POMONAG simultaneously considers accuracy, the number of parameters, multiply-accumulate operations (MACs), and inference latency. The experiments validate the performance of the proposed model. 1, The multi-objective optimization problem formulation in this work can be given first, which then can be solved by the proposed weighted factors in the reverse diffusion process. But maybe the authors can consider other ways to sovle this. For example, using four single reverse diffusion process each targeting one factor, as DiffusionNAG did, then using multi-objective optimization for further trade-off may also work well. 2, The theoretical analysis should be strehghen. One objective to many objective is a breakthrough, but such process needs more analysis or discussion. Current work lacks such in-depth thinking. 3, Several predictors are needed in this work, but the detailed information these predictors are missing. I have several questions about this work. 1, How to decide the scaling factors? Since the intervals are [1000,5000], [100,500], [100,500], [100,500], and the values seesm to be integer, then the whole factor space equals 4000 * 400 * 400 * 400, which is quite huge. And the authors present one setting for NASBench201 and other experiments, respectively, so I am wondering whether there is some method or strategy to choose such factors? 2, This work extends the basic motivation of DiffusionNAG, which is rather good and natural. Such extension include three more factors, including number of parameters, number of MACs, and the inference latency. But I am curious that, how about the performance of POMONAG if just considering adding one factor? 3, From one factor, say, accuracy, to three more factors seems strenghening the proposed POMONAG, but my question is, the working mechanism of DiffusionNAG and POMONAG the same different? Although the two diffusion processes consider different factors, which is the obvious difference, but the analysis or discussion is important to interpret this issue.