NASRec: Weight Sharing Neural Architecture Search for Recommender Systems

• URL: http://arxiv.org/abs/2207.07187v1
• Date: Thu, 14 Jul 2022 20:15:11 GMT
• Title: NASRec: Weight Sharing Neural Architecture Search for Recommender Systems
• Authors: Tunhou Zhang, Dehua Cheng, Yuchen He, Zhengxing Chen, Xiaoliang Dai, Liang Xiong, Feng Yan, Hai Li, Yiran Chen, Wei Wen
• Abstract summary: We propose NASRec, a paradigm that trains a single supernet and efficiently produces abundant models/sub-architectures by weight sharing. Our results on three Click-Through Rates (CTR) prediction benchmarks show that NASRec can outperform both manually designed models and existing NAS methods.
• Score: 40.54254555949057
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rise of deep neural networks provides an important driver in optimizing recommender systems. However, the success of recommender systems lies in delicate architecture fabrication, and thus calls for Neural Architecture Search (NAS) to further improve its modeling. We propose NASRec, a paradigm that trains a single supernet and efficiently produces abundant models/sub-architectures by weight sharing. To overcome the data multi-modality and architecture heterogeneity challenges in recommendation domain, NASRec establishes a large supernet (i.e., search space) to search the full architectures, with the supernet incorporating versatile operator choices and dense connectivity minimizing human prior for flexibility. The scale and heterogeneity in NASRec impose challenges in search, such as training inefficiency, operator-imbalance, and degraded rank correlation. We tackle these challenges by proposing single-operator any-connection sampling, operator-balancing interaction modules, and post-training fine-tuning. Our results on three Click-Through Rates (CTR) prediction benchmarks show that NASRec can outperform both manually designed models and existing NAS methods, achieving state-of-the-art performance.

Related papers

• DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions [121.05720140641189]
  We develop a family of models with the distilling neural architecture (DNA) techniques. Our proposed DNA models can rate all architecture candidates, as opposed to previous works that can only access a sub- search space using algorithms. Our models achieve state-of-the-art top-1 accuracy of 78.9% and 83.6% on ImageNet for a mobile convolutional network and a small vision transformer, respectively.
  arXiv  Detail & Related papers  (2024-03-02T22:16:47Z)
• Farthest Greedy Path Sampling for Two-shot Recommender Search [15.754449293550744]
  We introduce Farthest Greedy Path Sampling (FGPS), a new path sampling strategy that balances path quality and diversity. FGPS enhances path diversity to facilitate more comprehensive supernet exploration, while emphasizing path quality to ensure the effective identification and utilization of promising architectures. Our approach consistently achieves superior results, outperforming both manually designed and most NAS-based models.
  arXiv  Detail & Related papers  (2023-10-31T17:59:14Z)
• Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts [55.470959564665705]
  Weight-sharing supernets are crucial for performance estimation in cutting-edge neural search frameworks. The proposed method attains state-of-the-art (SoTA) performance in NAS for fast machine translation models. It excels in NAS for building memory-efficient task-agnostic BERT models.
  arXiv  Detail & Related papers  (2023-06-08T00:35:36Z)
• SuperNet in Neural Architecture Search: A Taxonomic Survey [14.037182039950505]
  This survey focuses on the supernet optimization that builds a neural network that assembles all the architectures as its sub models by using weight sharing. We aim to accomplish that by proposing them as solutions to the common challenges found in the literature: data-side optimization, poor rank correlation alleviation, and transferable NAS for a number of deployment scenarios.
  arXiv  Detail & Related papers  (2022-04-08T08:29:52Z)
• Enabling NAS with Automated Super-Network Generation [60.72821429802335]
  Recent Neural Architecture Search (NAS) solutions have produced impressive results training super-networks and then derivingworks. We present BootstrapNAS, a software framework for automatic generation of super-networks for NAS.
  arXiv  Detail & Related papers  (2021-12-20T21:45:48Z)
• BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule [95.56873042777316]
  Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost. This paper formulates the neural architecture search as a distribution learning problem through relaxing the architecture weights into Gaussian distributions. We demonstrate how the differentiable NAS benefits from Bayesian principles, enhancing exploration and improving stability.
  arXiv  Detail & Related papers  (2021-11-25T18:13:42Z)
• Searching Efficient Model-guided Deep Network for Image Denoising [61.65776576769698]
  We present a novel approach by connecting model-guided design with NAS (MoD-NAS) MoD-NAS employs a highly reusable width search strategy and a densely connected search block to automatically select the operations of each layer. Experimental results on several popular datasets show that our MoD-NAS has achieved even better PSNR performance than current state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-04-06T14:03:01Z)
• HMCNAS: Neural Architecture Search using Hidden Markov Chains and Bayesian Optimization [2.685668802278155]
  HMCNAS provides a step towards generalizing NAS, by providing a way to create competitive models, without requiring any human knowledge about the specific task.
  arXiv  Detail & Related papers  (2020-07-31T16:04:08Z)
• Federated Neural Architecture Search [19.573780215917477]
  We propose an automatic neural architecture search into the decentralized training, as a new DNN training paradigm called Federated Neural Architecture Search. We present FedNAS, a highly optimized framework for efficient federated NAS. Tested on large-scale datasets and typical CNN architectures, FedNAS achieves comparable model accuracy as state-of-the-art NAS algorithm.
  arXiv  Detail & Related papers  (2020-02-15T10:01:05Z)

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.