Learning to Skip the Middle Layers of Transformers

• URL: http://arxiv.org/abs/2506.21103v1
• Date: Thu, 26 Jun 2025 09:01:19 GMT
• Title: Learning to Skip the Middle Layers of Transformers
• Authors: Tim Lawson, Laurence Aitchison,
• Abstract summary: We propose a novel architecture that skips a variable number of layers from the middle outward.<n>In particular, a learned gating mechanism determines whether to bypass a symmetric span of central blocks based on the input.<n>Our approach does not achieve improvements in the trade-off between validation cross-entropy and estimated FLOPs compared to dense baselines with fewer layers.
• Score: 25.958907308877148
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conditional computation is a popular strategy to make Transformers more efficient. Existing methods often target individual modules (e.g., mixture-of-experts layers) or skip layers independently of one another. However, interpretability research has demonstrated that the middle layers of Transformers exhibit greater redundancy, and that early layers aggregate information into token positions. Guided by these insights, we propose a novel architecture that dynamically skips a variable number of layers from the middle outward. In particular, a learned gating mechanism determines whether to bypass a symmetric span of central blocks based on the input, and a gated attention mechanism prevents subsequent tokens from attending to skipped token positions. Residual norms are controlled with a 'sandwich' or 'perilayernorm' scheme and gate sparsity with an adaptive regularization loss. We had aimed to reduce compute requirements for 'simpler' tokens and potentially foster an emergent multi-level representational hierarchy but, at the scales investigated, our approach does not achieve improvements in the trade-off between validation cross-entropy and estimated FLOPs compared to dense baselines with fewer layers. We release our code at https://github.com/tim-lawson/skip-middle.

Related papers

• HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation [12.655334562608314]
  Federated Learning (FL) is a decentralized approach where multiple clients collaboratively train a shared global model without sharing their raw data.<n>This paper introduces Hierarchical Federated Domain Generalization (HFedDG), a novel scenario designed to investigate domain shift within hierarchical architectures.
  arXiv  Detail & Related papers  (2025-08-07T08:14:52Z)
• Find A Winning Sign: Sign Is All We Need to Win the Lottery [52.63674911541416]
  We show that a sparse network trained by an existing IP method can retain its basin of attraction if its parameter signs and normalization layer parameters are preserved.<n>To take a step closer to finding a winning ticket, we alleviate the reliance on normalization layer parameters by preventing high error barriers along the linear path between the sparse network trained by our method and its counterpart with normalization layer parameters.
  arXiv  Detail & Related papers  (2025-04-07T09:30:38Z)
• Pyramid Hierarchical Transformer for Hyperspectral Image Classification [1.9427851979929982]
  We propose a pyramid-based hierarchical transformer (PyFormer) This innovative approach organizes input data hierarchically into segments, each representing distinct abstraction levels. Results underscore the superiority of the proposed method over traditional approaches.
  arXiv  Detail & Related papers  (2024-04-23T11:41:19Z)
• MLP Can Be A Good Transformer Learner [73.01739251050076]
  Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. This paper introduces a novel strategy that simplifies vision transformers and reduces computational load through the selective removal of non-essential attention layers.
  arXiv  Detail & Related papers  (2024-04-08T16:40:15Z)
• GIFD: A Generative Gradient Inversion Method with Feature Domain Optimization [52.55628139825667]
  Federated Learning (FL) has emerged as a promising distributed machine learning framework to preserve clients' privacy. Recent studies find that an attacker can invert the shared gradients and recover sensitive data against an FL system by leveraging pre-trained generative adversarial networks (GAN) as prior knowledge. We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD), which disassembles the GAN model and searches the feature domains of the intermediate layers.
  arXiv  Detail & Related papers  (2023-08-09T04:34:21Z)
• Augmenting Convolutional networks with attention-based aggregation [55.97184767391253]
  We show how to augment any convolutional network with an attention-based global map to achieve non-local reasoning. We plug this learned aggregation layer with a simplistic patch-based convolutional network parametrized by 2 parameters (width and depth) It yields surprisingly competitive trade-offs between accuracy and complexity, in particular in terms of memory consumption.
  arXiv  Detail & Related papers  (2021-12-27T14:05:41Z)
• Rethinking Skip Connection with Layer Normalization in Transformers and ResNets [49.87919454950763]
  Skip connection is a widely-used technique to improve the performance of deep neural networks. In this work, we investigate how the scale factors in the effectiveness of the skip connection.
  arXiv  Detail & Related papers  (2021-05-15T11:44:49Z)
• Orthogonalizing Convolutional Layers with the Cayley Transform [83.73855414030646]
  We propose and evaluate an alternative approach to parameterize convolutional layers that are constrained to be orthogonal. We show that our method indeed preserves orthogonality to a high degree even for large convolutions.
  arXiv  Detail & Related papers  (2021-04-14T23:54:55Z)

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.