Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws

• URL: http://arxiv.org/abs/2505.24009v2
• Date: Fri, 06 Jun 2025 19:28:58 GMT
• Title: Diversity of Transformer Layers: One Aspect of Parameter Scaling Laws
• Authors: Hidetaka Kamigaito, Ying Zhang, Jingun Kwon, Katsuhiko Hayashi, Manabu Okumura, Taro Watanabe,
• Abstract summary: Transformers deliver outstanding performance across a wide range of tasks.<n>Their task-solving performance is improved by increasing parameter size.<n>This study focuses on layers and their size, which mainly decide the parameter size of Transformers.
• Score: 42.926341529639274
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformers deliver outstanding performance across a wide range of tasks and are now a dominant backbone architecture for large language models (LLMs). Their task-solving performance is improved by increasing parameter size, as shown in the recent studies on parameter scaling laws. Although recent mechanistic-interpretability studies have deepened our understanding of the internal behavior of Transformers by analyzing their residual stream, the relationship between these internal mechanisms and the parameter scaling laws remains unclear. To bridge this gap, we focus on layers and their size, which mainly decide the parameter size of Transformers. For this purpose, we first theoretically investigate the layers within the residual stream through a bias-diversity decomposition. The decomposition separates (i) bias, the error of each layer's output from the ground truth, and (ii) diversity, which indicates how much the outputs of each layer differ from each other. Analyzing Transformers under this theory reveals that performance improves when individual layers make predictions close to the correct answer and remain mutually diverse. We show that diversity becomes especially critical when individual layers' outputs are far from the ground truth. Finally, we introduce an information-theoretic diversity and show our main findings that adding layers enhances performance only when those layers behave differently, i.e., are diverse. We also reveal the performance gains from increasing the number of layers exhibit submodularity: marginal improvements diminish as additional layers increase, mirroring the logarithmic convergence predicted by the parameter scaling laws. Experiments on multiple semantic-understanding tasks with various LLMs empirically confirm the theoretical properties derived in this study.

Related papers

• Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models [12.112842686827669]
  Transformer based models have shown remarkable capabilities in sequence learning across a wide range of tasks.<n>We investigate the layerwise behavior of Transformers to uncover the mechanisms underlying their multi-task generalization ability.<n>Our explicit constructions align closely with empirical observations, providing theoretical support for the Transformer's effectiveness and efficiency on sequence learning across diverse tasks.
  arXiv  Detail & Related papers  (2025-06-02T17:39:31Z)
• Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective [55.90119819642064]
  We address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective.<n>This refers to the cumulative effect of reconstruction errors throughout the sparsification process.<n>We derive a simple yet effective approach to layer-wise sparsity allocation that mitigates this issue.
  arXiv  Detail & Related papers  (2025-02-20T17:51:10Z)
• Does Representation Matter? Exploring Intermediate Layers in Large Language Models [22.704926222438456]
  We investigate the quality of intermediate representations in large language models (LLMs)<n>We find that intermediate layers often yield more informative representations for downstream tasks than the final layers.<n>Our results illuminate the internal mechanics of LLMs and guide strategies for architectural optimization and training.
  arXiv  Detail & Related papers  (2024-12-12T18:48:51Z)
• What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis [8.008567379796666]
  We provide a fundamental understanding of what distinguishes the Transformer from the other architectures.<n>Our results suggest that various common architectural and optimization choices in Transformers can be traced back to their highly non-linear dependencies.
  arXiv  Detail & Related papers  (2024-10-14T18:15:02Z)
• Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization [88.5582111768376]
  We study the optimization of a Transformer composed of a self-attention layer with softmax followed by a fully connected layer under gradient descent on a certain data distribution model. Our results establish a sharp condition that can distinguish between the small test error phase and the large test error regime, based on the signal-to-noise ratio in the data model.
  arXiv  Detail & Related papers  (2024-09-28T13:24:11Z)
• Residual Stream Analysis with Multi-Layer SAEs [21.142967037533175]
  We introduce the multi-layer SAE (MLSAE), a single SAE trained on the residual stream activation vectors from every transformer layer.<n>We find that individual latents are often active at a single layer for a given token or prompt, but the layer at which an individual latent is active may differ for different tokens or prompts.<n>Our results represent a new approach to understanding how representations change as they flow through transformers.
  arXiv  Detail & Related papers  (2024-09-06T11:01:55Z)
• How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression [19.64743851296488]
  In this study, we consider a sparse linear regression problem and investigate how a trained multi-head transformer performs in-context learning. We experimentally discover that the utilization of multi-heads exhibits different patterns across layers. We demonstrate that such a preprocess-then-optimize algorithm can significantly outperform naive gradient descent and ridge regression algorithms.
  arXiv  Detail & Related papers  (2024-08-08T15:33:02Z)
• Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models [55.45444773200529]
  Large language models (LLMs) exhibit impressive natural language capabilities but suffer from hallucination. Recent work has focused on decoding techniques to improve factuality during inference.
  arXiv  Detail & Related papers  (2024-04-14T19:45:35Z)
• On the Long Range Abilities of Transformers [69.3021852589771]
  We demonstrate that minimal modifications to the transformer architecture can significantly enhance performance on the Long Range Arena benchmark. We identify that two key principles for long-range tasks are (i.e. incorporating an inductive bias towards smoothness, and (ii.e.) locality. As we show, integrating these ideas into the attention mechanism improves results with a negligible amount of additional computation and without any additional trainable parameters.
  arXiv  Detail & Related papers  (2023-11-28T09:21:48Z)
• Revisiting Over-smoothing in BERT from the Perspective of Graph [111.24636158179908]
  Recently over-smoothing phenomenon of Transformer-based models is observed in both vision and language fields. We find that layer normalization plays a key role in the over-smoothing issue of Transformer-based models. We consider hierarchical fusion strategies, which combine the representations from different layers adaptively to make the output more diverse.
  arXiv  Detail & Related papers  (2022-02-17T12:20:52Z)
• Deriving Differential Target Propagation from Iterating Approximate Inverses [91.3755431537592]
  We show that a particular form of target propagation, relying on learned inverses of each layer, which is differential, gives rise to an update rule which corresponds to an approximate Gauss-Newton gradient-based optimization. We consider several iterative calculations based on local auto-encoders at each layer in order to achieve more precise inversions for more accurate target propagation.
  arXiv  Detail & Related papers  (2020-07-29T22:34:45Z)

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.