Operational Abstractions of Neural Network Concepts via Topological Representations

Excerpt

arXiv:2610.05017v1 Announce Type: cross Abstract: Concept-based methods provide a semantic level for interpreting and manipulating learned representations, but existing editing approaches are typically specialized to particular interventions and do not provide a common and editable representation of concept organization. To achieve this, we introduce Topological Concept Representations (TCR), a post-hoc operational abstraction that jointly characterizes the concepts encoded in a learned represen