Dual feature-based and example-based explanation methods

• URL: http://arxiv.org/abs/2401.16294v1
• Date: Mon, 29 Jan 2024 16:53:04 GMT
• Title: Dual feature-based and example-based explanation methods
• Authors: Andrei V. Konstantinov, Boris V. Kozlov, Stanislav R. Kirpichenko, and Lev V. Utkin
• Abstract summary: A new approach to the local and global explanation is proposed. It is based on selecting a convex hull constructed for the finite number of points around an explained instance. The code of proposed algorithms is available.
• Score: 2.024925013349319
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A new approach to the local and global explanation is proposed. It is based on selecting a convex hull constructed for the finite number of points around an explained instance. The convex hull allows us to consider a dual representation of instances in the form of convex combinations of extreme points of a produced polytope. Instead of perturbing new instances in the Euclidean feature space, vectors of convex combination coefficients are uniformly generated from the unit simplex, and they form a new dual dataset. A dual linear surrogate model is trained on the dual dataset. The explanation feature importance values are computed by means of simple matrix calculations. The approach can be regarded as a modification of the well-known model LIME. The dual representation inherently allows us to get the example-based explanation. The neural additive model is also considered as a tool for implementing the example-based explanation approach. Many numerical experiments with real datasets are performed for studying the approach. The code of proposed algorithms is available.

Related papers

• Generative Unfolding with Distribution Mapping [0.0837622912636323]
  We show how to extend two morphing techniques, Schr"odinger Bridges and Direct Diffusion, in order to ensure that the models learn the correct conditional probabilities. Results are presented with a standard benchmark dataset of single jet substructure as well as for a new dataset describing a 22-dimensional phase space of Z + 2-jets.
  arXiv  Detail & Related papers  (2024-11-04T19:00:01Z)
• Efficient Fairness-Performance Pareto Front Computation [51.558848491038916]
  We show that optimal fair representations possess several useful structural properties. We then show that these approxing problems can be solved efficiently via concave programming methods.
  arXiv  Detail & Related papers  (2024-09-26T08:46:48Z)
• Sample Complexity Characterization for Linear Contextual MDPs [67.79455646673762]
  Contextual decision processes (CMDPs) describe a class of reinforcement learning problems in which the transition kernels and reward functions can change over time with different MDPs indexed by a context variable. CMDPs serve as an important framework to model many real-world applications with time-varying environments. We study CMDPs under two linear function approximation models: Model I with context-varying representations and common linear weights for all contexts; and Model II with common representations for all contexts and context-varying linear weights.
  arXiv  Detail & Related papers  (2024-02-05T03:25:04Z)
• Semi-Supervised Subspace Clustering via Tensor Low-Rank Representation [64.49871502193477]
  We propose a novel semi-supervised subspace clustering method, which is able to simultaneously augment the initial supervisory information and construct a discriminative affinity matrix. Comprehensive experimental results on six commonly-used benchmark datasets demonstrate the superiority of our method over state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-21T01:47:17Z)
• Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation [40.13463458124477]
  We decompose a contour matrix into eigencontours via the best rank-M approximation. We represent an object boundary by a linear combination of the M eigencontours. The proposed algorithm yields meaningful performances on instance segmentation datasets.
  arXiv  Detail & Related papers  (2022-03-29T06:14:38Z)
• EiGLasso for Scalable Sparse Kronecker-Sum Inverse Covariance Estimation [1.370633147306388]
  We introduce EiGLasso, a highly scalable method for sparse Kronecker-sum inverse covariance estimation. We show that EiGLasso achieves two to three orders-of-magnitude speed-up compared to the existing methods.
  arXiv  Detail & Related papers  (2021-05-20T16:22:50Z)
• Hybrid Trilinear and Bilinear Programming for Aligning Partially Overlapping Point Sets [85.71360365315128]
  In many applications, we need algorithms which can align partially overlapping point sets are invariant to the corresponding corresponding RPM algorithm. We first show that the objective is a cubic bound function. We then utilize the convex envelopes of trilinear and bilinear monomial transformations to derive its lower bound. We next develop a branch-and-bound (BnB) algorithm which only branches over the transformation variables and runs efficiently.
  arXiv  Detail & Related papers  (2021-01-19T04:24:23Z)
• Interpretable Machine Learning with an Ensemble of Gradient Boosting Machines [5.482532589225552]
  Method is based on using an ensemble of gradient boosting machines (GBMs) A lot of numerical experiments with an algorithm implementing the proposed method on synthetic and real datasets demonstrate its efficiency and properties for local and global interpretation.
  arXiv  Detail & Related papers  (2020-10-14T20:18:40Z)
• Model Fusion with Kullback--Leibler Divergence [58.20269014662046]
  We propose a method to fuse posterior distributions learned from heterogeneous datasets. Our algorithm relies on a mean field assumption for both the fused model and the individual dataset posteriors.
  arXiv  Detail & Related papers  (2020-07-13T03:27:45Z)
• The data-driven physical-based equations discovery using evolutionary approach [77.34726150561087]
  We describe the algorithm for the mathematical equations discovery from the given observations data. The algorithm combines genetic programming with the sparse regression. It could be used for governing analytical equation discovery as well as for partial differential equations (PDE) discovery.
  arXiv  Detail & Related papers  (2020-04-03T17:21:57Z)
• Convex Shape Representation with Binary Labels for Image Segmentation: Models and Fast Algorithms [7.847719964338735]
  We present a novel and effective binary representation for convex shapes. We show the equivalence between the shape convexity and some properties of the associated indicator function.
  arXiv  Detail & Related papers  (2020-02-22T01:55:20Z)

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.