From Clustering to Cluster Explanations via Neural Networks

Abstract

A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of Explainable AI (XAI) has so far mainly focused on supervised learning, in particular, deep neural network classifiers. In many practical problems however, label information is not given and the goal is instead to discover the underlying structure of the data, for example, its clusters. While powerful methods exist for extracting the cluster structure in data, they typically do not answer the question why a certain data point has been assigned to a given cluster. We propose a new framework that can, for the first time, explain cluster assignments in terms of input features in an efficient and reliable manner. It is based on the novel insight that clustering models can be rewritten as neural networks - or 'neuralized'. Cluster predictions of the obtained networks can then be quickly and accurately attributed to the input features. Several showcases demonstrate the ability of our method to assess the quality of learned clusters and to extract novel insights from the analyzed data and representations.

15 pages + supplement

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Methods for Interpreting and Understanding Deep Neural Networks
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Explaining the Unique Nature of Individual Gait Patterns with Deep Learning
• Explaining by Removing: A Unified Framework for Model Explanation
• Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
• Explaining and Interpreting LSTMs
• Building and Interpreting Deep Similarity Models
• XAI Beyond Classification: Interpretable Neural Clustering
• Interpretable Clustering via Optimal Trees

Cited by in corpus (27)

• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Deep Neural Networks and Tabular Data: A Survey
• Towards Explainable Artificial Intelligence
• Toward Explainable AI for Regression Models
• DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
• Building and Interpreting Deep Similarity Models
• Explainable $k$-Means and $k$-Medians Clustering
• Explanation-Guided Training for Cross-Domain Few-Shot Classification
• How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
• Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
• Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
• Extraction of Typical Operating Scenarios of New Power System Based on Deep Time Series Aggregation
• ExKMC: Expanding Explainable $k$-Means Clustering
• Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers
• Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
• Interpretation of Deep Temporal Representations by Selective Visualization of Internally Activated Nodes
• Identifying Dominant Industrial Sectors in Market States of the S&P 500 Financial Data
• Near-Optimal Explainable $k$-Means for All Dimensions
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Towards Robust Explanations for Deep Neural Networks
• Explaining Groups of Points in Low-Dimensional Representations
• Unveiling 3D Ocean Biogeochemical Provinces in the North Atlantic: A Systematic Comparison and Validation of Clustering Methods
• On the price of explainability for some clustering problems
• Fast and Accurate Explanations of Distance-Based Classifiers by Uncovering Latent Explanatory Structures
• Explaining Unsupervised Disease Staging in Huntington's Disease: Insights into Model Representations and Clusters
• Split and Expand: An inference-time improvement for Weakly Supervised Cell Instance Segmentation
• Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models