{"ID":452515,"CreatedAt":"2026-03-04T20:59:09Z","UpdatedAt":"2026-03-04T20:59:09Z","DeletedAt":null,"paper_url":"https://paperswithcode.com/paper/bitwidth-adaptive-quantization-aware-neural","arxiv_id":"2207.10188","title":"Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach","abstract":"Deep neural network quantization with adaptive bitwidths has gained increasing attention due to the ease of model deployment on various platforms with different resource budgets. In this paper, we propose a meta-learning approach to achieve this goal. Specifically, we propose MEBQAT, a simple yet effective way of bitwidth-adaptive quantization aware training (QAT) where meta-learning is effectively combined with QAT by redefining meta-learning tasks to incorporate bitwidths. After being deployed on a platform, MEBQAT allows the (meta-)trained model to be quantized to any candidate bitwidth then helps to conduct inference without much accuracy drop from quantization. Moreover, with a few-shot learning scenario, MEBQAT can also adapt a model to any bitwidth as well as any unseen target classes by adding conventional optimization or metric-based meta-learning. We design variants of MEBQAT to support both (1) a bitwidth-adaptive quantization scenario and (2) a new few-shot learning scenario where both quantization bitwidths and target classes are jointly adapted. We experimentally demonstrate their validity in multiple QAT schemes. By comparing their performance to (bitwidth-dedicated) QAT, existing bitwidth adaptive QAT and vanilla meta-learning, we find that merging bitwidths into meta-learning tasks achieves a higher level of robustness.","short_abstract":"By comparing their performance to (bitwidth-dedicated) QAT, existing bitwidth adaptive QAT and vanilla meta-learning, we find that merging bitwidths into meta-learning tasks achieves a higher level of robustness.","url_abs":"https://arxiv.org/abs/2207.10188v1","url_pdf":"https://arxiv.org/pdf/2207.10188v1.pdf","authors":"[\"Jiseok Youn\", \"Jaehun Song\", \"Hyung-Sin Kim\", \"Saewoong Bahk\"]","published":"2022-07-20T00:00:00Z","tasks":"[\"Few-Shot Learning\", \"Meta-Learning\", \"Quantization\"]","methods":"[\"AWARE\"]","has_code":false,"code_links":[{"ID":303664,"CreatedAt":"2026-03-04T21:00:12Z","UpdatedAt":"2026-03-04T21:00:12Z","DeletedAt":null,"paper_id":452515,"paper_url":"https://paperswithcode.com/paper/bitwidth-adaptive-quantization-aware-neural","paper_title":"Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach","repo_url":"https://github.com/jsjs0369/MEBQAT","is_official":true,"mentioned_in_paper":false,"mentioned_in_github":false,"framework":"pytorch","github_stars":0}]}