Unifying Attribution-Based Explanations Using Functional Decomposition
- URL: http://arxiv.org/abs/2412.13623v1
- Date: Wed, 18 Dec 2024 09:04:07 GMT
- Title: Unifying Attribution-Based Explanations Using Functional Decomposition
- Authors: Arne Gevaert, Yvan Saeys,
- Abstract summary: We propose a unifying framework of attribution-based explanation methods.
It provides a step towards a rigorous study of the similarities and differences of explanations.
- Score: 1.8216507818880976
- License:
- Abstract: The black box problem in machine learning has led to the introduction of an ever-increasing set of explanation methods for complex models. These explanations have different properties, which in turn has led to the problem of method selection: which explanation method is most suitable for a given use case? In this work, we propose a unifying framework of attribution-based explanation methods, which provides a step towards a rigorous study of the similarities and differences of explanations. We first introduce removal-based attribution methods (RBAMs), and show that an extensively broad selection of existing methods can be viewed as such RBAMs. We then introduce the canonical additive decomposition (CAD). This is a general construction for additively decomposing any function based on the central idea of removing (groups of) features. We proceed to show that indeed every valid additive decomposition is an instance of the CAD, and that any removal-based attribution method is associated with a specific CAD. Next, we show that any removal-based attribution method can be completely defined as a game-theoretic value or interaction index for a specific (possibly constant-shifted) cooperative game, which is defined using the corresponding CAD of the method. We then use this intrinsic connection to define formal descriptions of specific behaviours of explanation methods, which we also call functional axioms, and identify sufficient conditions on the corresponding CAD and game-theoretic value or interaction index of an attribution method under which the attribution method is guaranteed to adhere to these functional axioms. Finally, we show how this unifying framework can be used to develop new, efficient approximations for existing explanation methods.
Related papers
- Uncertainty Quantification with Bayesian Higher Order ReLU KANs [0.0]
We introduce the first method of uncertainty quantification in the domain of Kolmogorov-Arnold Networks, specifically focusing on (Higher Order) ReLUKANs.
We validate our method through a series of closure tests, including simple one-dimensional functions.
We demonstrate the method's ability to correctly identify functional dependencies introduced through the inclusion of a term.
arXiv Detail & Related papers (2024-10-02T15:57:18Z) - Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation [54.50526986788175]
Recent advances in efficient sequence modeling have led to attention-free layers, such as Mamba, RWKV, and various gated RNNs.
We present a unified view of these models, formulating such layers as implicit causal self-attention layers.
Our framework compares the underlying mechanisms on similar grounds for different layers and provides a direct means for applying explainability methods.
arXiv Detail & Related papers (2024-05-26T09:57:45Z) - Composable Part-Based Manipulation [61.48634521323737]
We propose composable part-based manipulation (CPM) to improve learning and generalization of robotic manipulation skills.
CPM comprises a collection of composable diffusion models, where each model captures a different inter-object correspondence.
We validate our approach in both simulated and real-world scenarios, demonstrating its effectiveness in achieving robust and generalized manipulation capabilities.
arXiv Detail & Related papers (2024-05-09T16:04:14Z) - Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse
Actions, Interventions and Sparse Temporal Dependencies [58.179981892921056]
This work introduces a novel principle for disentanglement we call mechanism sparsity regularization.
We propose a representation learning method that induces disentanglement by simultaneously learning the latent factors.
We show that the latent factors can be recovered by regularizing the learned causal graph to be sparse.
arXiv Detail & Related papers (2024-01-10T02:38:21Z) - Object Representations as Fixed Points: Training Iterative Refinement
Algorithms with Implicit Differentiation [88.14365009076907]
Iterative refinement is a useful paradigm for representation learning.
We develop an implicit differentiation approach that improves the stability and tractability of training.
arXiv Detail & Related papers (2022-07-02T10:00:35Z) - Which Explanation Should I Choose? A Function Approximation Perspective
to Characterizing Post hoc Explanations [16.678003262147346]
We show that popular explanation methods are instances of the local function approximation (LFA) framework.
We set forth a guiding principle based on the function approximation perspective, considering a method to be effective if it recovers the underlying model.
We empirically validate our theoretical results using various real world datasets, model classes, and prediction tasks.
arXiv Detail & Related papers (2022-06-02T19:09:30Z) - 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) - Topological Representations of Local Explanations [8.559625821116454]
We propose a topology-based framework to extract a simplified representation from a set of local explanations.
We demonstrate that our framework can not only reliably identify differences between explainability techniques but also provides stable representations.
arXiv Detail & Related papers (2022-01-06T17:46:45Z) - Explaining by Removing: A Unified Framework for Model Explanation [14.50261153230204]
Removal-based explanations are based on the principle of simulating feature removal to quantify each feature's influence.
We develop a framework that characterizes each method along three dimensions: 1) how the method removes features, 2) what model behavior the method explains, and 3) how the method summarizes each feature's influence.
This newly understood class of explanation methods has rich connections that we examine using tools that have been largely overlooked by the explainability literature.
arXiv Detail & Related papers (2020-11-21T00:47:48Z) - Feature Removal Is a Unifying Principle for Model Explanation Methods [14.50261153230204]
We examine the literature and find that many methods are based on a shared principle of explaining by removing.
We develop a framework for removal-based explanations that characterizes each method along three dimensions.
Our framework unifies 26 existing methods, including several of the most widely used approaches.
arXiv Detail & Related papers (2020-11-06T22:37:55Z) - Evaluating the Disentanglement of Deep Generative Models through
Manifold Topology [66.06153115971732]
We present a method for quantifying disentanglement that only uses the generative model.
We empirically evaluate several state-of-the-art models across multiple datasets.
arXiv Detail & Related papers (2020-06-05T20:54:11Z)
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.