Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures

• URL: http://arxiv.org/abs/2505.07070v1
• Date: Sun, 11 May 2025 17:44:14 GMT
• Title: Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures
• Authors: Francesco Cagnetta, Alessandro Favero, Antonio Sclocchi, Matthieu Wyart,
• Abstract summary: We derive theoretical scaling laws for neural network performance on synthetic datasets.<n>We validate that convolutional networks, whose structure aligns with that of the generative process through locality and weight sharing, enjoy a faster scaling of performance.<n>This finding clarifies the architectural biases underlying neural scaling laws and highlights how representation learning is shaped by the interaction between model architecture and the statistical properties of data.
• Score: 49.19753720526998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: How do neural language models acquire a language's structure when trained for next-token prediction? We address this question by deriving theoretical scaling laws for neural network performance on synthetic datasets generated by the Random Hierarchy Model (RHM) -- an ensemble of probabilistic context-free grammars designed to capture the hierarchical structure of natural language while remaining analytically tractable. Previously, we developed a theory of representation learning based on data correlations that explains how deep learning models capture the hierarchical structure of the data sequentially, one layer at a time. Here, we extend our theoretical framework to account for architectural differences. In particular, we predict and empirically validate that convolutional networks, whose structure aligns with that of the generative process through locality and weight sharing, enjoy a faster scaling of performance compared to transformer models, which rely on global self-attention mechanisms. This finding clarifies the architectural biases underlying neural scaling laws and highlights how representation learning is shaped by the interaction between model architecture and the statistical properties of data.

Related papers

• Language Embedding Meets Dynamic Graph: A New Exploration for Neural Architecture Representation Learning [38.323486764309]
  We introduce LeDG-Former, an innovative framework that addresses limitations through the synergistic integration of language-based semantic embedding and dynamic graph representation learning.<n>Specifically, we propose a language embedding framework where both neural architectures and hardware platform specifications are projected into a unified semantic space.<n>Our framework achieves superior performance on the cell-structured NAS-Bench-101 and NAS-Bench-201 datasets.
  arXiv  Detail & Related papers  (2025-06-09T13:20:02Z)
• Analysis and Visualization of Linguistic Structures in Large Language Models: Neural Representations of Verb-Particle Constructions in BERT [0.0]
  This study investigates the internal representations of verb-particle combinations within large language models (LLMs)<n>We analyse the representational efficacy of its layers for various verb-particle constructions such as 'agree on', 'come back', and 'give up'<n>Results show that BERT's middle layers most effectively capture syntactic structures, with significant variability in representational accuracy across different verb categories.
  arXiv  Detail & Related papers  (2024-12-19T09:21:39Z)
• Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers [74.96551626420188]
  Transformers trained on natural language data have been shown to learn its hierarchical structure and generalize to sentences with unseen syntactic structures.<n>We investigate sources of inductive bias in transformer models and their training that could cause such generalization behavior to emerge.
  arXiv  Detail & Related papers  (2024-04-25T07:10:29Z)
• LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning [73.98142349171552]
  LOGICSEG is a holistic visual semantic that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. During fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. These designs together make LOGICSEG a general and compact neural-logic machine that is readily integrated into existing segmentation models.
  arXiv  Detail & Related papers  (2023-09-24T05:43:19Z)
• Homological Convolutional Neural Networks [4.615338063719135]
  We propose a novel deep learning architecture that exploits the data structural organization through topologically constrained network representations. We test our model on 18 benchmark datasets against 5 classic machine learning and 3 deep learning models.
  arXiv  Detail & Related papers  (2023-08-26T08:48:51Z)
• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• Constructing Word-Context-Coupled Space Aligned with Associative Knowledge Relations for Interpretable Language Modeling [0.0]
  The black-box structure of the deep neural network in pre-trained language models seriously limits the interpretability of the language modeling process. A Word-Context-Coupled Space (W2CSpace) is proposed by introducing the alignment processing between uninterpretable neural representation and interpretable statistical logic. Our language model can achieve better performance and highly credible interpretable ability compared to related state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-19T09:26:02Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• A Semi-Supervised Assessor of Neural Architectures [157.76189339451565]
  We employ an auto-encoder to discover meaningful representations of neural architectures. A graph convolutional neural network is introduced to predict the performance of architectures.
  arXiv  Detail & Related papers  (2020-05-14T09:02:33Z)

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.