ScoresActivation: A New Activation Function for Model Agnostic Global Explainability by Design

• URL: http://arxiv.org/abs/2511.13809v1
• Date: Mon, 17 Nov 2025 18:10:34 GMT
• Title: ScoresActivation: A New Activation Function for Model Agnostic Global Explainability by Design
• Authors: Emanuel Covaci, Fabian Galis, Radu Balan, Daniela Zaharie, Darian Onchis,
• Abstract summary: We introduce a novel differentiable approach to global explainability by design.<n>We integrate feature importance estimation directly into model training.<n>Our approach yields globally faithful, stable feature rankings aligned with SHAP values and ground-truth feature importance.
• Score: 0.815557531820863
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding the decision of large deep learning models is a critical challenge for building transparent and trustworthy systems. Although the current post hoc explanation methods offer valuable insights into feature importance, they are inherently disconnected from the model training process, limiting their faithfulness and utility. In this work, we introduce a novel differentiable approach to global explainability by design, integrating feature importance estimation directly into model training. Central to our method is the ScoresActivation function, a feature-ranking mechanism embedded within the learning pipeline. This integration enables models to prioritize features according to their contribution to predictive performance in a differentiable and end-to-end trainable manner. Evaluations across benchmark datasets show that our approach yields globally faithful, stable feature rankings aligned with SHAP values and ground-truth feature importance, while maintaining high predictive performance. Moreover, feature scoring is 150 times faster than the classical SHAP method, requiring only 2 seconds during training compared to SHAP's 300 seconds for feature ranking in the same configuration. Our method also improves classification accuracy by 11.24% with 10 features (5 relevant) and 29.33% with 16 features (5 relevant, 11 irrelevant), demonstrating robustness to irrelevant inputs. This work bridges the gap between model accuracy and interpretability, offering a scalable framework for inherently explainable machine learning.

Related papers

• Fair Feature Importance Scores via Feature Occlusion and Permutation [41.73851747821022]
  We propose two model-agnostic approaches to measure fair feature importance.<n>First, we compare model fairness before and after permuting feature values.<n>Second, we evaluate the fairness of models trained with and without a given feature.
  arXiv  Detail & Related papers  (2026-02-09T21:02:52Z)
• CID: Measuring Feature Importance Through Counterfactual Distributions [0.7559720049837458]
  This paper introduces a novel post-hoc local feature importance method called Counterfactual Importance Distribution (CID)<n>We generate two sets of positive and negative counterfactuals, model their distributions using Kernel Density Estimation, and rank features based on a distributional dissimilarity measure.<n>We showcase the effectiveness of our method by comparing with well-established local feature importance explainers.
  arXiv  Detail & Related papers  (2025-11-19T11:57:59Z)
• Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning [51.92313556418432]
  Supervised fine-tuning (SFT) plays a critical role for pretrained large language models (LLMs)<n>We suggest categorizing tokens within each corpus into two parts -- positive and negative tokens -- based on whether they are useful to improve model performance.<n>We conduct experiments on well-established benchmarks, finding that this forgetting mechanism not only improves overall model performance and also facilitate more diverse model responses.
  arXiv  Detail & Related papers  (2025-08-06T11:22:23Z)
• Enhancing Training Data Attribution with Representational Optimization [57.61977909113113]
  Training data attribution methods aim to measure how training data impacts a model's predictions.<n>We propose AirRep, a representation-based approach that closes this gap by learning task-specific and model-aligned representations explicitly for TDA.<n>AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence.
  arXiv  Detail & Related papers  (2025-05-24T05:17:53Z)
• FORCE: Feature-Oriented Representation with Clustering and Explanation [0.0]
  We propose a SHAP based supervised deep learning framework FORCE.<n>It relies on two-stage usage of SHAP values in the neural network architecture.<n>We show that FORCE led to dramatic improvements in overall performance as compared to networks that did not incorporate the latent feature and attention framework.
  arXiv  Detail & Related papers  (2025-04-07T22:05:50Z)
• Iterative Feature Boosting for Explainable Speech Emotion Recognition [17.568724398229232]
  We present a new supervised SER method based on an efficient feature engineering approach. We pay particular attention to the explainability of results to evaluate feature relevance and refine feature sets. The proposed method outperforms human-level performance (HLP) and state-of-the-art machine learning methods in emotion recognition on the TESS dataset.
  arXiv  Detail & Related papers  (2024-05-30T15:44:27Z)
• Robust Learning with Progressive Data Expansion Against Spurious Correlation [65.83104529677234]
  We study the learning process of a two-layer nonlinear convolutional neural network in the presence of spurious features. Our analysis suggests that imbalanced data groups and easily learnable spurious features can lead to the dominance of spurious features during the learning process. We propose a new training algorithm called PDE that efficiently enhances the model's robustness for a better worst-group performance.
  arXiv  Detail & Related papers  (2023-06-08T05:44:06Z)
• Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction [49.15931834209624]
  We present the first benchmark that simulates the evaluation of open information extraction models in the real world.<n>We design and annotate a large-scale testbed in which each example is a knowledge-invariant clique.<n>By further elaborating the robustness metric, a model is judged to be robust if its performance is consistently accurate on the overall cliques.
  arXiv  Detail & Related papers  (2023-05-23T12:05:09Z)
• Plex: Towards Reliability using Pretrained Large Model Extensions [69.13326436826227]
  We develop ViT-Plex and T5-Plex, pretrained large model extensions for vision and language modalities, respectively. Plex greatly improves the state-of-the-art across reliability tasks, and simplifies the traditional protocol. We demonstrate scaling effects over model sizes up to 1B parameters and pretraining dataset sizes up to 4B examples.
  arXiv  Detail & Related papers  (2022-07-15T11:39:37Z)
• MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation [132.77005365032468]
  We propose a novel framework of Model-Agnostic Counterfactual Explanation (MACE) In our MACE approach, we propose a novel RL-based method for finding good counterfactual examples and a gradient-less descent method for improving proximity. Experiments on public datasets validate the effectiveness with better validity, sparsity and proximity.
  arXiv  Detail & Related papers  (2022-05-31T04:57:06Z)
• Adversarial Infidelity Learning for Model Interpretation [43.37354056251584]
  We propose a Model-agnostic Effective Efficient Direct (MEED) IFS framework for model interpretation. Our framework mitigates concerns about sanity, shortcuts, model identifiability, and information transmission. Our AIL mechanism can help learn the desired conditional distribution between selected features and targets.
  arXiv  Detail & Related papers  (2020-06-09T16:27:17Z)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

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.