Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
cs.LG, cs.AI
Submitted: 2026-02-18
Updated: 2026-11-06
Comments: Accepted at NeurIPS 2026. 41 pages, 10 figures. Code: https://github.com/givasile/calm-paper
Code: https://github.com/givasile/CALM
License: http://creativecommons.org/licenses/by/4.0/
The gist: Generalized additive models (GAMs) offer high interpretability through independent univariate feature effects but underfit when interactions are present in data.
Terminology
Abstract
Generalized additive models (GAMs) offer high interpretability through independent univariate feature effects but underfit when interactions are present in data. GA squared Ms add selected pairwise interactions, which improves accuracy, but sacrifices interpretability. We propose Conditionally Additive Local Models (CALMs), a new model class that narrows this trade-off: it stays close to GAMs in interpretability and close to GA squared Ms in accuracy. CALMs allow multiple univariate shape functions per feature, each active in different regions of the input space. These regions are defined independently for each feature as simple logical conditions (thresholds) on the features it interacts with. As a result, effects remain locally additive while varying across subregions to capture interactions. We further propose a principled distillation-based training pipeline that identifies homogeneous regions with limited interactions and fits interpretable shape functions via region-aware backfitting. Experiments on diverse classification and regression tasks show that CALMs never underperform GAMs, often beat them and achieve accuracy broadly comparable to GA squared Ms, while preserving the univariate auditability that GA squared Ms forfeit.
Sources
- Towards A Rigorous Science of Interpretable Machine Learning
- TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
- Surrogate Locally-Interpretable Models with Supervised Machine Learning Algorithms
- Interpretable machine learning: definitions, methods, and applications
- PMLB v1.0: An open source dataset collection for benchmarking machine learning methods
- GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning