Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects

• URL: http://arxiv.org/abs/2602.16503v1
• Date: Wed, 18 Feb 2026 14:45:33 GMT
• Title: Interpretability-by-Design with Accurate Locally Additive Models and Conditional Feature Effects
• Authors: Vasilis Gkolemis, Loukas Kavouras, Dimitrios Kyriakopoulos, Konstantinos Tsopelas, Dimitrios Rontogiannis, Giuseppe Casalicchio, Theodore Dalamagas, Christos Diou,
• Abstract summary: We propose emphConditionally Additive Local Models (CALMs)<n>CALMs balance interpretability of GAMs with the accuracy of GA$2$Ms.<n>Experiments show CALMs consistently outperform GAMs and achieve accuracy comparable with GA$2$Ms.
• Score: 6.312016976793988
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalized additive models (GAMs) offer interpretability through independent univariate feature effects but underfit when interactions are present in data. GA$^2$Ms add selected pairwise interactions which improves accuracy, but sacrifices interpretability and limits model auditing. We propose \emph{Conditionally Additive Local Models} (CALMs), a new model class, that balances the interpretability of GAMs with the accuracy of GA$^2$Ms. 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 consistently outperform GAMs and achieve accuracy comparable with GA$^2$Ms. Overall, CALMs offer a compelling trade-off between predictive accuracy and interpretability.

Related papers

• Multiplicative-Additive Constrained Models:Toward Joint Visualization of Interactive and Independent Effects [0.0]
  Interpretability is one of the considerations when applying machine learning to high-stakes fields such as healthcare.<n>Generalized Additive Models (GAMs) enhance interpretability by visualizing shape functions.<n>We introduce Multiplicative-Additive Constrained Models (MACMs), which augment CESR with an additive part to disentangle the intertwined coefficients of its interactive and independent terms.
  arXiv  Detail & Related papers  (2025-09-26T06:08:31Z)
• Decorrelated feature importance from local sample weighting [0.0]
  Local sample weighting (losaw) can be integrated into many machine learning algorithms to improve Feature importance (FI) scores.<n>We show how losaw can be integrated within decision tree-based ML methods and within mini-batch training of neural networks.
  arXiv  Detail & Related papers  (2025-08-08T14:11:18Z)
• Unified modality separation: A vision-language framework for unsupervised domain adaptation [60.8391821117794]
  Unsupervised domain adaptation (UDA) enables models trained on a labeled source domain to handle new unlabeled domains.<n>We propose a unified modality separation framework that accommodates both modality-specific and modality-invariant components.<n>Our methods achieve up to 9% performance gain with 9 times of computational efficiencies.
  arXiv  Detail & Related papers  (2025-08-07T02:51:10Z)
• GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs [56.93583799109029]
  GrAInS is an inference-time steering approach that operates across both language-only and vision-language models and tasks.<n>During inference, GrAInS hidden activations at transformer layers guided by token-level attribution signals, and normalizes activations to preserve representational scale.<n>It consistently outperforms both fine-tuning and existing steering baselines.
  arXiv  Detail & Related papers  (2025-07-24T02:34:13Z)
• Generalized Sparse Additive Model with Unknown Link Function [19.807823040041896]
  We propose a new sparse additive model, named generalized sparse additive model with unknown link function (GSAMUL) The component functions are estimated by B-spline basis and the unknown link function is estimated by a multi-layer perceptron (MLP) network. In applications, experimental evaluations on both synthetic and real world data sets consistently validate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2024-10-08T13:13:58Z)
• Delta-AI: Local objectives for amortized inference in sparse graphical models [64.5938437823851]
  We present a new algorithm for amortized inference in sparse probabilistic graphical models (PGMs) Our approach is based on the observation that when the sampling of variables in a PGM is seen as a sequence of actions taken by an agent, sparsity of the PGM enables local credit assignment in the agent's policy learning objective. We illustrate $Delta$-AI's effectiveness for sampling from synthetic PGMs and training latent variable models with sparse factor structure.
  arXiv  Detail & Related papers  (2023-10-03T20:37:03Z)
• Regionally Additive Models: Explainable-by-design models minimizing feature interactions [8.118449359076438]
  Generalized Additive Models (GAMs) are widely used explainable-by-design models in various applications. In ML problems where the output depends on multiple features simultaneously, GAMs fail to capture the interaction terms of the underlying function. We propose Regionally Additive Models (RAMs), a novel class of explainable-by-design models.
  arXiv  Detail & Related papers  (2023-09-21T16:16:22Z)
• SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision [54.16430358203348]
  We propose a simple but effective slimmable semantic segmentation (SlimSeg) method, which can be executed at different capacities during inference. We show that our proposed SlimSeg with various mainstream networks can produce flexible models that provide dynamic adjustment of computational cost and better performance.
  arXiv  Detail & Related papers  (2022-07-13T14:41:05Z)
• Instrumental Variable-Driven Domain Generalization with Unobserved Confounders [53.735614014067394]
  Domain generalization (DG) aims to learn from multiple source domains a model that can generalize well on unseen target domains. We propose an instrumental variable-driven DG method (IV-DG) by removing the bias of the unobserved confounders with two-stage learning. In the first stage, it learns the conditional distribution of the input features of one domain given input features of another domain. In the second stage, it estimates the relationship by predicting labels with the learned conditional distribution.
  arXiv  Detail & Related papers  (2021-10-04T13:32:57Z)
• Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately [83.68135652247496]
  A natural remedy is to remove spurious features from the model. We show that removal of spurious features can decrease accuracy due to inductive biases. We also show that robust self-training can remove spurious features without affecting the overall accuracy.
  arXiv  Detail & Related papers  (2020-12-07T23:08:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.