What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks

• URL: http://arxiv.org/abs/2404.01601v1
• Date: Tue, 2 Apr 2024 02:45:12 GMT
• Title: What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks
• Authors: Xingwu Chen, Difan Zou,
• Abstract summary: We show a transformer with only one attention layer can excel in memorization but falls short in other tasks. We identify a class of simple operations that a single attention layer can execute, and show that the complex tasks can be approached as the combinations of these simple operations.
• Score: 15.874604623294427
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the capabilities of the transformer architecture with varying depth. Specifically, we designed a novel set of sequence learning tasks to systematically evaluate and comprehend how the depth of transformer affects its ability to perform memorization, reasoning, generalization, and contextual generalization. We show a transformer with only one attention layer can excel in memorization but falls short in other tasks. Then, we show that exhibiting reasoning and generalization ability requires the transformer to have at least two attention layers, while context generalization ability may necessitate three attention layers. Additionally, we identify a class of simple operations that a single attention layer can execute, and show that the complex tasks can be approached as the combinations of these simple operations and thus can be resolved by stacking multiple attention layers. This sheds light on studying more practical and complex tasks beyond our design. Numerical experiments corroborate our theoretical findings.

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)
• How Transformers Learn Regular Language Recognition: A Theoretical Study on Training Dynamics and Implicit Bias [48.9399496805422]
  We focus on two representative tasks in the category of regular language recognition, known as even pairs' and parity check'<n>Our goal is to explore how a one-layer transformer, consisting of an attention layer followed by a linear layer, learns to solve these tasks.
  arXiv  Detail & Related papers  (2025-05-02T00:07:35Z)
• Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers [0.0]
  I introduce the retrieval problem, a simple reasoning task that can be solved only by transformers with a minimum number of layers. I demonstrate that large language models can solve the task under different prompting formulations without any fine-tuning. I find that successful learning occurs only under the presence of an implicit curriculum.
  arXiv  Detail & Related papers  (2024-11-18T23:12:13Z)
• One-Layer Transformer Provably Learns One-Nearest Neighbor In Context [48.4979348643494]
  We study the capability of one-layer transformers learning the one-nearest neighbor rule. A single softmax attention layer can successfully learn to behave like a one-nearest neighbor.
  arXiv  Detail & Related papers  (2024-11-16T16:12:42Z)
• In-Context Learning with Representations: Contextual Generalization of Trained Transformers [66.78052387054593]
  In-context learning (ICL) refers to a capability of pretrained large language models, which can learn a new task given a few examples during inference. This paper investigates the training dynamics of transformers by gradient descent through the lens of non-linear regression tasks.
  arXiv  Detail & Related papers  (2024-08-19T16:47:46Z)
• Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers [16.26331213222281]
  We analyze the solutions simple transformer blocks implement when tackling the histogram task.<n>This task reveals a complex interplay between predictive performance, vocabulary and embedding sizes, token-mixing mechanisms, and feed-forward layer capacity.
  arXiv  Detail & Related papers  (2024-07-16T09:48:10Z)
• Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers? [57.04803703952721]
  Large language models (LLMs) have shown remarkable performances across a wide range of tasks. However, the mechanisms by which these models encode tasks of varying complexities remain poorly understood. We introduce the idea of Concept Depth'' to suggest that more complex concepts are typically acquired in deeper layers.
  arXiv  Detail & Related papers  (2024-04-10T14:56:40Z)
• Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding [52.723297744257536]
  Pre-trained language models (LMs) have shown effectiveness in scientific literature understanding tasks. We propose a multi-task contrastive learning framework, SciMult, to facilitate common knowledge sharing across different literature understanding tasks.
  arXiv  Detail & Related papers  (2023-05-23T16:47:22Z)
• Systematic Generalization and Emergent Structures in Transformers Trained on Structured Tasks [6.525090891505941]
  We show how a causal transformer can perform a set of algorithmic tasks, including copying, sorting, and hierarchical compositions. We show that two-layer transformers learn generalizable solutions to multi-level problems and develop signs of systematic task decomposition. These results provide key insights into how transformer models may be capable of decomposing complex decisions into reusable, multi-level policies.
  arXiv  Detail & Related papers  (2022-10-02T00:46:36Z)
• Unveiling Transformers with LEGO: a synthetic reasoning task [23.535488809197787]
  We study how the transformer architecture learns to follow a chain of reasoning. In some data regime the trained transformer finds "shortcut" solutions to follow the chain of reasoning. We find that one can prevent such shortcut with appropriate architecture modification or careful data preparation.
  arXiv  Detail & Related papers  (2022-06-09T06:30:17Z)
• Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization [101.72755769194677]
  We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph. Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks. Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
  arXiv  Detail & Related papers  (2022-05-25T10:44:25Z)
• Evolving Attention with Residual Convolutions [29.305149185821882]
  We propose a novel mechanism based on evolving attention to improve the performance of transformers. The proposed attention mechanism achieves significant performance improvement over various state-of-the-art models for multiple tasks.
  arXiv  Detail & Related papers  (2021-02-20T15:24:06Z)
• Multi-Head Attention: Collaborate Instead of Concatenate [85.71058762269374]
  We propose a collaborative multi-head attention layer that enables heads to learn shared projections. Experiments confirm that sharing key/query dimensions can be exploited in language understanding, machine translation and vision.
  arXiv  Detail & Related papers  (2020-06-29T20:28:52Z)

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.