ZeroLM: Data-Free Transformer Architecture Search for Language Models

• URL: http://arxiv.org/abs/2503.18646v1
• Date: Mon, 24 Mar 2025 13:11:22 GMT
• Title: ZeroLM: Data-Free Transformer Architecture Search for Language Models
• Authors: Zhen-Song Chen, Hong-Wei Ding, Xian-Jia Wang, Witold Pedrycz,
• Abstract summary: Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
• Score: 54.83882149157548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural architecture search (NAS) provides a systematic framework for automating the design of neural network architectures, yet its widespread adoption is hindered by prohibitive computational requirements. Existing zero-cost proxy methods, while reducing search overhead, demonstrate inadequate performance in architecture ranking tasks, particularly for Transformer-based models where they often underperform simple parameter counting metrics. Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity. This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics computation while decomposing Transformer architectures into functionally distinct sub-modules, thereby optimizing the balance of their contributions to overall performance. Our comprehensive evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark. The proposed method exhibits exceptional computational efficiency while maintaining robust performance across diverse NAS benchmark tasks, offering a practical solution for large-scale architecture search.

Related papers

• Meta knowledge assisted Evolutionary Neural Architecture Search [38.55611683982936]
  This paper introduces an efficient EC-based NAS method to solve problems via an innovative meta-learning framework. An adaptive surrogate model is designed through an adaptive threshold to select the potential architectures. Experiments on CIFAR-10, CIFAR-100, and ImageNet1K datasets demonstrate that the proposed method achieves high performance comparable to that of many state-of-the-art peer methods.
  arXiv  Detail & Related papers  (2025-04-30T11:43:07Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• TG-NAS: Leveraging Zero-Cost Proxies with Transformer and Graph Convolution Networks for Efficient Neural Architecture Search [1.30891455653235]
  TG-NAS aims to create training-free proxies for architecture performance prediction. We introduce TG-NAS, a novel model-based universal proxy that leverages a transformer-based operator embedding generator and a graph convolution network (GCN) to predict architecture performance. TG-NAS achieves up to 300X improvements in search efficiency compared to previous SOTA ZC proxy methods.
  arXiv  Detail & Related papers  (2024-03-30T07:25:30Z)
• Mechanistic Design and Scaling of Hybrid Architectures [114.3129802943915]
  We identify and test new hybrid architectures constructed from a variety of computational primitives. We experimentally validate the resulting architectures via an extensive compute-optimal and a new state-optimal scaling law analysis. We find MAD synthetics to correlate with compute-optimal perplexity, enabling accurate evaluation of new architectures.
  arXiv  Detail & Related papers  (2024-03-26T16:33:12Z)
• Training-free Neural Architecture Search for RNNs and Transformers [0.0]
  We develop a new training-free metric, named hidden covariance, that predicts the trained performance of an RNN architecture. We find that the current search space paradigm for transformer architectures is not optimized for training-free neural architecture search.
  arXiv  Detail & Related papers  (2023-06-01T02:06:13Z)
• Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search [96.20505710087392]
  We propose a Shapley value based method to evaluate operation contribution (Shapley-NAS) for neural architecture search. We show that our method outperforms the state-of-the-art methods by a considerable margin with light search cost.
  arXiv  Detail & Related papers  (2022-06-20T14:41:49Z)
• FreeREA: Training-Free Evolution-based Architecture Search [17.202375422110553]
  FreeREA is a custom cell-based evolution NAS algorithm that exploits an optimised combination of training-free metrics to rank architectures. Our experiments, carried out on the common benchmarks NAS-Bench-101 and NATS-Bench, demonstrate that i) FreeREA is a fast, efficient, and effective search method for models automatic design.
  arXiv  Detail & Related papers  (2022-06-17T11:16:28Z)
• Learning Where To Look -- Generative NAS is Surprisingly Efficient [11.83842808044211]
  We propose a generative model, paired with a surrogate predictor, that iteratively learns to generate samples from increasingly promising latent subspaces. This approach leads to very effective and efficient architecture search, while keeping the query amount low.
  arXiv  Detail & Related papers  (2022-03-16T16:27:11Z)
• Rethinking Architecture Selection in Differentiable NAS [74.61723678821049]
  Differentiable Neural Architecture Search is one of the most popular NAS methods for its search efficiency and simplicity. We propose an alternative perturbation-based architecture selection that directly measures each operation's influence on the supernet. We find that several failure modes of DARTS can be greatly alleviated with the proposed selection method.
  arXiv  Detail & Related papers  (2021-08-10T00:53:39Z)
• iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients [75.41173109807735]
  Differentiable ARchiTecture Search (DARTS) has recently become the mainstream of neural architecture search (NAS) We tackle the hypergradient computation in DARTS based on the implicit function theorem. We show that the architecture optimisation with the proposed method, named iDARTS, is expected to converge to a stationary point.
  arXiv  Detail & Related papers  (2021-06-21T00:44:11Z)

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.