Relational Composition in Neural Networks: A Survey and Call to Action

• URL: http://arxiv.org/abs/2407.14662v1
• Date: Fri, 19 Jul 2024 20:50:57 GMT
• Title: Relational Composition in Neural Networks: A Survey and Call to Action
• Authors: Martin Wattenberg, Fernanda B. Viégas,
• Abstract summary: Many neural nets appear to represent data as linear combinations of "feature vectors" We argue that this success is incomplete without an understanding of relational composition.
• Score: 54.47858085003077
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many neural nets appear to represent data as linear combinations of "feature vectors." Algorithms for discovering these vectors have seen impressive recent success. However, we argue that this success is incomplete without an understanding of relational composition: how (or whether) neural nets combine feature vectors to represent more complicated relationships. To facilitate research in this area, this paper offers a guided tour of various relational mechanisms that have been proposed, along with preliminary analysis of how such mechanisms might affect the search for interpretable features. We end with a series of promising areas for empirical research, which may help determine how neural networks represent structured data.

Related papers

• Interpreting Neural Networks through Mahalanobis Distance [0.0]
  This paper introduces a theoretical framework that connects neural network linear layers with the Mahalanobis distance. Although this work is theoretical and does not include empirical data, the proposed distance-based interpretation has the potential to enhance model robustness, improve generalization, and provide more intuitive explanations of neural network decisions.
  arXiv  Detail & Related papers  (2024-10-25T07:21:44Z)
• 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)
• Neuro-symbolic computing with spiking neural networks [0.6035125735474387]
  We extend previous work on spike-based graph algorithms by demonstrating how symbolic and multi-relational information can be encoded using spiking neurons. The introduced framework is enabled by combining the graph embedding paradigm and the recent progress in training spiking neural networks using error backpropagation.
  arXiv  Detail & Related papers  (2022-08-04T10:49:34Z)
• 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)
• Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
  We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs. By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
  arXiv  Detail & Related papers  (2022-02-01T17:11:13Z)
• 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)
• How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks [80.55378250013496]
  We study how neural networks trained by gradient descent extrapolate what they learn outside the support of the training distribution. Graph Neural Networks (GNNs) have shown some success in more complex tasks.
  arXiv  Detail & Related papers  (2020-09-24T17:48:59Z)
• Complexity for deep neural networks and other characteristics of deep feature representations [0.0]
  We define a notion of complexity, which quantifies the nonlinearity of the computation of a neural network. We investigate these observables both for trained networks as well as explore their dynamics during training.
  arXiv  Detail & Related papers  (2020-06-08T17:59:30Z)
• Investigating the Compositional Structure Of Deep Neural Networks [1.8899300124593645]
  We introduce a novel theoretical framework based on the compositional structure of piecewise linear activation functions. It is possible to characterize the instances of the input data with respect to both the predicted label and the specific (linear) transformation used to perform predictions. Preliminary tests on the MNIST dataset show that our method can group input instances with regard to their similarity in the internal representation of the neural network.
  arXiv  Detail & Related papers  (2020-02-17T14:16:17Z)
• Neural Rule Ensembles: Encoding Sparse Feature Interactions into Neural Networks [3.7277730514654555]
  We use decision trees to capture relevant features and their interactions and define a mapping to encode extracted relationships into a neural network. At the same time through feature selection it enables learning of compact representations compared to state of the art tree-based approaches.
  arXiv  Detail & Related papers  (2020-02-11T11:22:20Z)

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.