LGAINEMLSep 30, 2018

Interpretable Neuron Structuring with Graph Spectral Regularization

arXiv:1810.00424v56 citations
Originality Incremental advance
AI Analysis

This addresses the issue of interpretability in neural networks for researchers and practitioners, but it is incremental as it builds on existing regularization methods.

The paper tackles the problem of neural networks being black boxes by proposing Graph Spectral Regularization to make hidden layers more interpretable without significantly impacting performance, showing uses like cluster indication and visualization in biological and image datasets.

While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making hidden layers more interpretable without significantly impacting performance on the primary task. Taking inspiration from spatial organization and localization of neuron activations in biological networks, we use a graph Laplacian penalty to structure the activations within a layer. This penalty encourages activations to be smooth either on a predetermined graph or on a feature-space graph learned from the data via co-activations of a hidden layer of the neural network. We show numerous uses for this additional structure including cluster indication and visualization in biological and image data sets.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes