When Representations Align: Universality in Representation Learning Dynamics

• URL: http://arxiv.org/abs/2402.09142v2
• Date: Fri, 5 Jul 2024 09:42:01 GMT
• Title: When Representations Align: Universality in Representation Learning Dynamics
• Authors: Loek van Rossem, Andrew M. Saxe,
• Abstract summary: We derive an effective theory of representation learning under the assumption that the encoding map from input to hidden representation and the decoding map from representation to output are arbitrary smooth functions. We show through experiments that the effective theory describes aspects of representation learning dynamics across a range of deep networks with different activation functions and architectures.
• Score: 8.188549368578704
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks come in many sizes and architectures. The choice of architecture, in conjunction with the dataset and learning algorithm, is commonly understood to affect the learned neural representations. Yet, recent results have shown that different architectures learn representations with striking qualitative similarities. Here we derive an effective theory of representation learning under the assumption that the encoding map from input to hidden representation and the decoding map from representation to output are arbitrary smooth functions. This theory schematizes representation learning dynamics in the regime of complex, large architectures, where hidden representations are not strongly constrained by the parametrization. We show through experiments that the effective theory describes aspects of representation learning dynamics across a range of deep networks with different activation functions and architectures, and exhibits phenomena similar to the "rich" and "lazy" regime. While many network behaviors depend quantitatively on architecture, our findings point to certain behaviors that are widely conserved once models are sufficiently flexible.

Related papers

• From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks [47.13391046553908]
  In artificial networks, the effectiveness of these models relies on their ability to build task specific representation. Prior studies highlight that different initializations can place networks in either a lazy regime, where representations remain static, or a rich/feature learning regime, where representations evolve dynamically. These solutions capture the evolution of representations and the Neural Kernel across the spectrum from the rich to the lazy regimes.
  arXiv  Detail & Related papers  (2024-09-22T23:19:04Z)
• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Learned feature representations are biased by complexity, learning order, position, and more [4.529707672004383]
  We explore surprising dissociations between representation and computation. We train various deep learning architectures to compute multiple abstract features about their inputs. We find that their learned feature representations are systematically biased towards representing some features more strongly than others.
  arXiv  Detail & Related papers  (2024-05-09T15:34:15Z)
• 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)
• Weisfeiler and Leman Go Relational [4.29881872550313]
  We investigate the limitations in the expressive power of the well-known GCN and Composition GCN architectures. We introduce the $k$-RN architecture that provably overcomes the limitations of the above two architectures.
  arXiv  Detail & Related papers  (2022-11-30T15:56:46Z)
• Complexity of Representations in Deep Learning [2.0219767626075438]
  We analyze the effectiveness of the learned representations in separating the classes from a data complexity perspective. We show how the data complexity evolves through the network, how it changes during training, and how it is impacted by the network design and the availability of training samples.
  arXiv  Detail & Related papers  (2022-09-01T15:20:21Z)
• The Neural Race Reduction: Dynamics of Abstraction in Gated Networks [12.130628846129973]
  We introduce the Gated Deep Linear Network framework that schematizes how pathways of information flow impact learning dynamics. We derive an exact reduction and, for certain cases, exact solutions to the dynamics of learning. Our work gives rise to general hypotheses relating neural architecture to learning and provides a mathematical approach towards understanding the design of more complex architectures.
  arXiv  Detail & Related papers  (2022-07-21T12:01:03Z)
• On Neural Architecture Inductive Biases for Relational Tasks [76.18938462270503]
  We introduce a simple architecture based on similarity-distribution scores which we name Compositional Network generalization (CoRelNet) We find that simple architectural choices can outperform existing models in out-of-distribution generalizations.
  arXiv  Detail & Related papers  (2022-06-09T16:24:01Z)
• 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 neural anisotropic view of underspecification in deep learning [60.119023683371736]
  We show that the way neural networks handle the underspecification of problems is highly dependent on the data representation. Our results highlight that understanding the architectural inductive bias in deep learning is fundamental to address the fairness, robustness, and generalization of these systems.
  arXiv  Detail & Related papers  (2021-04-29T14:31:09Z)
• 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.