Towards Regression-Free Neural Networks for Diverse Compute Platforms

• URL: http://arxiv.org/abs/2209.13740v1
• Date: Tue, 27 Sep 2022 23:19:16 GMT
• Title: Towards Regression-Free Neural Networks for Diverse Compute Platforms
• Authors: Rahul Duggal, Hao Zhou, Shuo Yang, Jun Fang, Yuanjun Xiong, Wei Xia
• Abstract summary: We introduce REGression constrained Neural Architecture Search (REG-NAS) to design a family of highly accurate models that engender fewer negative flips. REG-NAS consists of two components: (1) A novel architecture constraint that enables a larger model to contain all the weights of the smaller one thus maximizing weight sharing. We demonstrate that regnas can successfully find desirable architectures with few negative flips in three popular architecture search spaces.
• Score: 50.64489250972764
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important. Our work tackles the emergent problem of reducing predictive inconsistencies arising as negative flips: test samples that are correctly predicted by a less accurate model, but incorrectly by a more accurate one. We introduce REGression constrained Neural Architecture Search (REG-NAS) to design a family of highly accurate models that engender fewer negative flips. REG-NAS consists of two components: (1) A novel architecture constraint that enables a larger model to contain all the weights of the smaller one thus maximizing weight sharing. This idea stems from our observation that larger weight sharing among networks leads to similar sample-wise predictions and results in fewer negative flips; (2) A novel search reward that incorporates both Top-1 accuracy and negative flips in the architecture search metric. We demonstrate that \regnas can successfully find desirable architectures with few negative flips in three popular architecture search spaces. Compared to the existing state-of-the-art approach, REG-NAS enables 33-48% relative reduction of negative flips.

Related papers

• Representation Similarity: A Better Guidance of DNN Layer Sharing for Edge Computing without Training [3.792729116385123]
  We propose a new model merging scheme by sharing representations at the edge, guided by representation similarity S. We show that S is extremely highly correlated with merged model's accuracy with Pearson Correlation Coefficient |r| > 0.94 than other metrics.
  arXiv  Detail & Related papers  (2024-10-15T03:35:54Z)
• Improved Generalization of Weight Space Networks via Augmentations [56.571475005291035]
  Learning in deep weight spaces (DWS) is an emerging research direction, with applications to 2D and 3D neural fields (INRs, NeRFs) We empirically analyze the reasons for this overfitting and find that a key reason is the lack of diversity in DWS datasets. To address this, we explore strategies for data augmentation in weight spaces and propose a MixUp method adapted for weight spaces.
  arXiv  Detail & Related papers  (2024-02-06T15:34:44Z)
• AffineGlue: Joint Matching and Robust Estimation [74.04609046690913]
  We propose AffineGlue, a method for joint two-view feature matching and robust estimation. AffineGlue selects potential matches from one-to-many correspondences to estimate minimal models. Guided matching is then used to find matches consistent with the model, suffering less from the ambiguities of one-to-one matches.
  arXiv  Detail & Related papers  (2023-07-28T08:05:36Z)
• PRE-NAS: Predictor-assisted Evolutionary Neural Architecture Search [34.06028035262884]
  We propose a novel evolutionary-based NAS strategy, Predictor-assisted E-NAS (PRE-NAS) PRE-NAS leverages new evolutionary search strategies and integrates high-fidelity weight inheritance over generations. Experiments on NAS-Bench-201 and DARTS search spaces show that PRE-NAS can outperform state-of-the-art NAS methods.
  arXiv  Detail & Related papers  (2022-04-27T06:40:39Z)
• Model Architecture Adaption for Bayesian Neural Networks [9.978961706999833]
  We show a novel network architecture search (NAS) that optimize BNNs for both accuracy and uncertainty. In our experiments, the searched models show comparable uncertainty ability and accuracy compared to the state-of-the-art (deep ensemble)
  arXiv  Detail & Related papers  (2022-02-09T10:58:50Z)
• IQNAS: Interpretable Integer Quadratic Programming Neural Architecture Search [40.77061519007659]
  A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS) Previous methods use complicated predictors for the accuracy of the network. We introduce Interpretable Quadratic programming Neural Architecture Search (IQNAS)
  arXiv  Detail & Related papers  (2021-10-24T09:45:00Z)
• Weak NAS Predictors Are All You Need [91.11570424233709]
  Recent predictor-based NAS approaches attempt to solve the problem with two key steps: sampling some architecture-performance pairs and fitting a proxy accuracy predictor. We shift the paradigm from finding a complicated predictor that covers the whole architecture space to a set of weaker predictors that progressively move towards the high-performance sub-space. Our method costs fewer samples to find the top-performance architectures on NAS-Bench-101 and NAS-Bench-201, and it achieves the state-of-the-art ImageNet performance on the NASNet search space.
  arXiv  Detail & Related papers  (2021-02-21T01:58:43Z)
• FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining [65.39532971991778]
  We present an accuracy predictor that scores architecture and training recipes jointly, guiding both sample selection and ranking. We run fast evolutionary searches in just CPU minutes to generate architecture-recipe pairs for a variety of resource constraints. FBNetV3 makes up a family of state-of-the-art compact neural networks that outperform both automatically and manually-designed competitors.
  arXiv  Detail & Related papers  (2020-06-03T05:20:21Z)
• BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models [59.95091850331499]
  We propose BigNAS, an approach that challenges the conventional wisdom that post-processing of the weights is necessary to get good prediction accuracies. Our discovered model family, BigNASModels, achieve top-1 accuracies ranging from 76.5% to 80.9%.
  arXiv  Detail & Related papers  (2020-03-24T23:00:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.