Detecting Modularity in Deep Neural Networks

• URL: http://arxiv.org/abs/2110.08058v1
• Date: Wed, 13 Oct 2021 20:33:30 GMT
• Title: Detecting Modularity in Deep Neural Networks
• Authors: Shlomi Hod, Stephen Casper, Daniel Filan, Cody Wild, Andrew Critch, Stuart Russell
• Abstract summary: We consider the problem of assessing the modularity exhibited by a partitioning of a network's neurons. We propose two proxies for this: importance, which reflects how crucial sets of neurons are to network performance; and coherence, which reflects how consistently their neurons associate with features of the inputs. We show that these partitionings, even ones based only on weights, reveal groups of neurons that are important and coherent.
• Score: 8.967870619902211
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A neural network is modular to the extent that parts of its computational graph (i.e. structure) can be represented as performing some comprehensible subtask relevant to the overall task (i.e. functionality). Are modern deep neural networks modular? How can this be quantified? In this paper, we consider the problem of assessing the modularity exhibited by a partitioning of a network's neurons. We propose two proxies for this: importance, which reflects how crucial sets of neurons are to network performance; and coherence, which reflects how consistently their neurons associate with features of the inputs. To measure these proxies, we develop a set of statistical methods based on techniques conventionally used to interpret individual neurons. We apply the proxies to partitionings generated by spectrally clustering a graph representation of the network's neurons with edges determined either by network weights or correlations of activations. We show that these partitionings, even ones based only on weights (i.e. strictly from non-runtime analysis), reveal groups of neurons that are important and coherent. These results suggest that graph-based partitioning can reveal modularity and help us understand how deep neural networks function.

Related papers

• 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)
• Graph Neural Networks for Learning Equivariant Representations of Neural Networks [55.04145324152541]
  We propose to represent neural networks as computational graphs of parameters. Our approach enables a single model to encode neural computational graphs with diverse architectures. We showcase the effectiveness of our method on a wide range of tasks, including classification and editing of implicit neural representations.
  arXiv  Detail & Related papers  (2024-03-18T18:01:01Z)
• Identifying Interpretable Visual Features in Artificial and Biological Neural Systems [3.604033202771937]
  Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features. Many neurons exhibit $textitmixed selectivity$, i.e., they represent multiple unrelated features. We propose an automated method for quantifying visual interpretability and an approach for finding meaningful directions in network activation space.
  arXiv  Detail & Related papers  (2023-10-17T17:41:28Z)
• Neural Networks are Decision Trees [0.0]
  We show that any neural network having piece-wise linear activation functions can be represented as a decision tree. The representation is equivalence and not an approximation, thus keeping the accuracy of the neural network exactly as is.
  arXiv  Detail & Related papers  (2022-10-11T06:49:51Z)
• Modeling Structure with Undirected Neural Networks [20.506232306308977]
  We propose undirected neural networks, a flexible framework for specifying computations that can be performed in any order. We demonstrate the effectiveness of undirected neural architectures, both unstructured and structured, on a range of tasks.
  arXiv  Detail & Related papers  (2022-02-08T10:06:51Z)
• 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)
• 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)
• And/or trade-off in artificial neurons: impact on adversarial robustness [91.3755431537592]
  Presence of sufficient number of OR-like neurons in a network can lead to classification brittleness and increased vulnerability to adversarial attacks. We define AND-like neurons and propose measures to increase their proportion in the network. Experimental results on the MNIST dataset suggest that our approach holds promise as a direction for further exploration.
  arXiv  Detail & Related papers  (2021-02-15T08:19:05Z)
• The Representation Theory of Neural Networks [7.724617675868718]
  We show that neural networks can be represented via the mathematical theory of quiver representations. We show that network quivers gently adapt to common neural network concepts. We also provide a quiver representation model to understand how a neural network creates representations from the data.
  arXiv  Detail & Related papers  (2020-07-23T19:02:14Z)
• Graph Structure of Neural Networks [104.33754950606298]
  We show how the graph structure of neural networks affect their predictive performance. A "sweet spot" of relational graphs leads to neural networks with significantly improved predictive performance. Top-performing neural networks have graph structure surprisingly similar to those of real biological neural networks.
  arXiv  Detail & Related papers  (2020-07-13T17:59:31Z)

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.