paper-with-me

Papers

Compositionality Unlocks Deep Interpretable Models

2025-04-03 · Thomas Dooms, Ward Gauderis, Geraint A. Wiggins, Jose Oramas

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.

📄 PDF Abstract BibTeX arXiv:2504.02667

Code (0)

등록된 구현이 없습니다.

Tasks

Model CompressionTensor Networks

Similar Papers 제목 키워드 기반

Concept-Best-Matching: Evaluating Compositionality in Emergent Communication

2024-03-17 · Boaz Carmeli, Yonatan Belinkov, Ron Meir

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

2022-01-28 · Takeshi D. Itoh, Takatomi Kubo, Kazushi Ikeda

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 Summarization

Diorama: Unleashing Zero-shot Single-view 3D Scene Modeling

2024-11-29 · Qirui Wu, Denys Iliash, Daniel Ritchie, Manolis Savva 외

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 Estimation

Enhancing Cross-Modal Medical Image Segmentation through Compositionality

2024-08-21 · Aniek Eijpe, Valentina Corbetta, Kalina Chupetlovska, Regina Beets-Tan 외

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+2

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization

2023-06-11 · Thomas Fel, Thibaut Boissin, Victor Boutin, Agustin Picard 외

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…