Beyond Additive Decompositions: Interpretability Through Separability

• URL: http://arxiv.org/abs/2605.31200v2
• Date: Mon, 01 Jun 2026 11:12:14 GMT
• Title: Beyond Additive Decompositions: Interpretability Through Separability
• Abstract summary: Interpretable machine learning requires models that are accurate and structurally faithful to the data.<n>We propose Separation Learning (TSL), a regression model that learns a sum of rank-1 products of uni-feature functions via a stagewise greedy procedure with refitting.<n>We establish approximation-rate guarantees for functions with bounded mixed $p$-th order partial derivatives and demonstrate that TSL competes with black-box models on regression benchmarks.
• Score: 1.92520187564634
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Interpretable machine learning requires models that are accurate and structurally faithful to the data. Existing explainability methods rely heavily on additive representations (e.g., Generalized Additive Models (GAMs), SHapley Additive exPlanations (SHAP), functional ANOVA), which can suffer from signal cancellation and off-support extrapolation in the presence of strong interactions. We propose Tensor Separation Learning (TSL), a regression model that learns a sum of rank-1 products of univariate per-feature functions via a stagewise greedy procedure with orthogonal refitting. By enforcing separability, TSL avoids the information loss inherent in additive projections caused by marginalizing higher-order interactions. The learned TSL model can be fully reconstructed from first-order partial dependence functions, up to constant factors. This stage-wise correspondence ensures that the resulting visualizations are faithful to the fitted components. We establish approximation-rate guarantees for functions with bounded mixed $p$-th order partial derivatives and demonstrate that TSL competes with black-box models on regression benchmarks.

Related papers

• Knowing when to trust machine-learned interatomic potentials [1.5586922787941984]
  We show that PROBE produces a per-prediction reliability probability that tracks actual error without modification to the underlying model.<n> PROBE is post-hoc and architecture-agnostic, and is directly deployable on any machine-learned interatomic potential.
  arXiv  Detail & Related papers  (2026-05-01T13:21:56Z)
• Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective [60.45433515408158]
  We show that long Chain-of-Thought (CoT) serves as a decisive decision-maker for the top option but fails to function as a granular distribution calibrator for ambiguous tasks.<n>We observe a distinct "decoupled mechanism": while CoT improves distributional alignment, final accuracy is dictated by CoT content.
  arXiv  Detail & Related papers  (2026-01-06T16:26:40Z)
• Score-Based Model for Low-Rank Tensor Recovery [49.158601255093416]
  Low-rank tensor decompositions (TDs) provide an effective framework for multiway data analysis.<n>Traditional TD methods rely on predefined structural assumptions, such as CP or Tucker decompositions.<n>We propose a score-based model that eliminates the need for predefined structural or distributional assumptions.
  arXiv  Detail & Related papers  (2025-06-27T15:05:37Z)
• Identifiable Convex-Concave Regression via Sub-gradient Regularised Least Squares [1.9580473532948397]
  We propose a novel nonparametric regression method that models complex input-relationships as the sum of convex and concave components.<n>The method-ICCNLS-decomposes sub-constrained shape-constrained additive decomposition.
  arXiv  Detail & Related papers  (2025-06-22T15:53:12Z)
• Disentanglement with Factor Quantized Variational Autoencoders [11.597012266516332]
  We propose a discrete variational autoencoder (VAE) based model where the ground truth information about the generative factors are not provided to the model.<n>We demonstrate the advantages of learning discrete representations over learning continuous representations in facilitating disentanglement.<n>Our method called FactorQVAE combines optimization based disentanglement approaches with discrete representation learning.
  arXiv  Detail & Related papers  (2024-09-23T09:33:53Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models [42.17166746027585]
  We introduce a bidirectional weighted graph-based framework to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $beta$-VAE based module to extract factors as the initial nodes of the graph. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement.
  arXiv  Detail & Related papers  (2024-07-26T15:32:21Z)
• Multi-Granularity Semantic Revision for Large Language Model Distillation [66.03746866578274]
  We propose a multi-granularity semantic revision method for LLM distillation. At the sequence level, we propose a sequence correction and re-generation strategy. At the token level, we design a distribution adaptive clipping Kullback-Leibler loss as the distillation objective function. At the span level, we leverage the span priors of a sequence to compute the probability correlations within spans, and constrain the teacher and student's probability correlations to be consistent.
  arXiv  Detail & Related papers  (2024-07-14T03:51:49Z)
• Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals [14.741951369068877]
  We find that ubiquitous time series (TS) forecasting models are prone to severe overfitting. We introduce a dual-stream and subtraction mechanism, which is a deep Boosting ensemble learning method. The proposed method outperform existing state-of-the-art methods, yielding an average performance improvement of 11.9% across various datasets.
  arXiv  Detail & Related papers  (2024-02-04T03:54:31Z)
• Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression [53.15502562048627]
  Recent work has built the connection between self-supervised learning and the approximation of the top eigenspace of a graph Laplacian operator. This work delves into a statistical analysis of augmentation-based pretraining.
  arXiv  Detail & Related papers  (2023-06-01T15:18:55Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• Improving Contrastive Learning with Model Augmentation [123.05700988581806]
  The sequential recommendation aims at predicting the next items in user behaviors, which can be solved by characterizing item relationships in sequences. Due to the data sparsity and noise issues in sequences, a new self-supervised learning (SSL) paradigm is proposed to improve the performance.
  arXiv  Detail & Related papers  (2022-03-25T06:12:58Z)

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.