Compositionality Unlocks Deep Interpretable Models
We propose $\chi$-net, an intrinsically interpretable architecture combining the compositional multilinear structure of tensor networks with the expressivity and efficiency of deep neural networks. $\chi$-nets retain equal accuracy compared to their baseline counterparts. Our novel, efficient diagonalisation algorithm, ODT, reveals linear low-rank structure in a multilayer SVHN model. We leverage this toward formal weight-based interpretability and model compression.
Code (0)
등록된 구현이 없습니다.
Tasks
Model CompressionTensor NetworksSimilar Papers 제목 키워드 기반
Concept-Best-Matching: Evaluating Compositionality in Emergent Communication
Artificial agents that learn to communicate in order to accomplish a given task acquire communication protocols that are typically opaque to a human. A large body of work has attempted to evaluate the emergent communicat…
Compositionality-Aware Graph2Seq Learning
Graphs are a highly expressive data structure, but it is often difficult for humans to find patterns from a complex graph. Hence, generating human-interpretable sequences from graphs have gained interest, called graph2se…
Code SummarizationSource Code SummarizationDiorama: Unleashing Zero-shot Single-view 3D Scene Modeling
Reconstructing structured 3D scenes from RGB images using CAD objects unlocks efficient and compact scene representations that maintain compositionality and interactability. Existing works propose training-heavy methods …
3D Shape RetrievalPose EstimationEnhancing Cross-Modal Medical Image Segmentation through Compositionality
Cross-modal medical image segmentation presents a significant challenge, as different imaging modalities produce images with varying resolutions, contrasts, and appearances of anatomical structures. We introduce composit…
DisentanglementImage SegmentationInductive BiasMedical Image Segmentation+2Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Feature visualization has gained substantial popularity, particularly after the influential work by Olah et al. in 2017, which established it as a crucial tool for explainability. However, its widespread adoption has bee…