Latent Space Topology Evolution in Multilayer Perceptrons
This provides interpretable insights into how MLPs organize data for classification, which is an incremental advancement for researchers in machine learning interpretability.
The paper tackles the problem of interpreting internal representations in Multilayer Perceptrons (MLPs) by introducing a topological framework that captures how data topology evolves across network layers, enabling the identification of redundant layers and critical topological transitions in experiments on synthetic and real-world medical data.
This paper introduces a topological framework for interpreting the internal representations of Multilayer Perceptrons (MLPs). We construct a simplicial tower, a sequence of simplicial complexes connected by simplicial maps, that captures how data topology evolves across network layers. Our approach enables bi-persistence analysis: layer persistence tracks topological features within each layer across scales, while MLP persistence reveals how these features transform through the network. We prove stability theorems for our topological descriptors and establish that linear separability in latent spaces is related to disconnected components in the nerve complexes. To make our framework practical, we develop a combinatorial algorithm for computing MLP persistence and introduce trajectory-based visualisations that track data flow through the network. Experiments on synthetic and real-world medical data demonstrate our method's ability to identify redundant layers, reveal critical topological transitions, and provide interpretable insights into how MLPs progressively organise data for classification.