CUBE: Contrastive Understanding by Balanced Experiments
Post-hoc explanation depends on how model queries are organized. We propose CUBE, a design-based framework that explains a trained predictive model through balanced low--high probes. Selected variables define factors, designed feature-level combinations define query conditions, and model predictions are summarized as factorial contrasts. CUBE reports main effects and pairwise interactions as controlled readings of average and conditional response changes over a declared design space. Experiments on synthetic and real tabular tasks show that CUBE recovers dominant learned effect structure, clarifies query-efficient identifiability, and supports screening--follow-up refinement.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
D-Cube: Exploiting Hyper-Features of Diffusion Model for Robust Medical Classification
The integration of deep learning technologies in medical imaging aims to enhance the efficiency and accuracy of cancer diagnosis, particularly for pancreatic and breast cancers, which present significant diagnostic chall…
Contrastive LearningDiagnosticfeature selectionRevisiting Randomization with the Cube Method
We propose a novel randomization approach for randomized controlled trials (RCTs), based on the cube method developed by Deville and Till\'e (2004). The cube method allows for the selection of balanced samples across var…
Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition
Deep neural networks perform poorly on heavily class-imbalanced datasets. Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognitio…
Contrastive LearningLong-tail LearningRepresentation LearningTheoretical Analysis of Contrastive Learning under Imbalanced Data: From Training Dynamics to a Pruning Solution
Contrastive learning has emerged as a powerful framework for learning generalizable representations, yet its theoretical understanding remains limited, particularly under imbalanced data distributions that are prevalent …
Contrastive LearningExploring Balanced Feature Spaces for Representation Learning
Existing self-supervised learning (SSL) methods are mostly applied for training representation models from artificially balanced datasets (e.g., ImageNet). It is unclear how well they will perform in the practical scenar…
Contrastive LearningLong-tail LearningRepresentation LearningSelf-Supervised Learning