Realistic Counterfactual Explanations by Learned Relations

• URL: http://arxiv.org/abs/2202.07356v1
• Date: Tue, 15 Feb 2022 12:33:51 GMT
• Title: Realistic Counterfactual Explanations by Learned Relations
• Authors: Xintao Xiang and Artem Lenskiy
• Abstract summary: We propose a novel approach to realistic counterfactual explanations that preserve relationships between data attributes. The model directly learns the relationships by a variational auto-encoder without domain knowledge and then learns to disturb the latent space accordingly.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many existing methods of counterfactual explanations ignore the intrinsic relationships between data attributes and thus fail to generate realistic counterfactuals. Moreover, the existing methods that account for relationships between data attributes require domain knowledge, which limits their applicability in complex real-world applications. In this paper, we propose a novel approach to realistic counterfactual explanations that preserve relationships between data attributes. The model directly learns the relationships by a variational auto-encoder without domain knowledge and then learns to disturb the latent space accordingly. We conduct extensive experiments on both synthetic and real-world datasets. The results demonstrate that the proposed method learns relationships from the data and preserves these relationships in generated counterfactuals.

Related papers

• MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities [72.68829963458408]
  We present MergeNet, which learns to bridge the gap of parameter spaces of heterogeneous models. The core mechanism of MergeNet lies in the parameter adapter, which operates by querying the source model's low-rank parameters. MergeNet is learned alongside both models, allowing our framework to dynamically transfer and adapt knowledge relevant to the current stage.
  arXiv  Detail & Related papers  (2024-04-20T08:34:39Z)
• Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation [28.91572089512024]
  Pair Fashion Explanation dataset is a unique resource that has been curated to illuminate compatibility relationships. We propose an innovative two-stage pipeline model that leverages this dataset. Our experiments showcase the model's potential in crafting descriptions that are knowledgeable, aligned with ground-truth matching correlations, and that produce understandable and informative descriptions.
  arXiv  Detail & Related papers  (2023-12-17T05:45:49Z)
• Mode Connectivity and Data Heterogeneity of Federated Learning [8.677832361022809]
  Federated learning (FL) enables multiple clients to train a model while keeping their data private collaboratively. Previous studies have shown that data heterogeneity between clients leads to drifts across client updates. We perform empirical and theoretical studies on the relationship between client and global modes.
  arXiv  Detail & Related papers  (2023-09-29T01:49:03Z)
• On the Joint Interaction of Models, Data, and Features [82.60073661644435]
  We introduce a new tool, the interaction tensor, for empirically analyzing the interaction between data and model through features. Based on these observations, we propose a conceptual framework for feature learning. Under this framework, the expected accuracy for a single hypothesis and agreement for a pair of hypotheses can both be derived in closed-form.
  arXiv  Detail & Related papers  (2023-06-07T21:35:26Z)
• On Neural Architecture Inductive Biases for Relational Tasks [76.18938462270503]
  We introduce a simple architecture based on similarity-distribution scores which we name Compositional Network generalization (CoRelNet) We find that simple architectural choices can outperform existing models in out-of-distribution generalizations.
  arXiv  Detail & Related papers  (2022-06-09T16:24:01Z)
• Attention-based Adversarial Appearance Learning of Augmented Pedestrians [49.25430012369125]
  We propose a method to synthesize realistic data for the pedestrian recognition task. Our approach utilizes an attention mechanism driven by an adversarial loss to learn domain discrepancies. Our experiments confirm that the proposed adaptation method is robust to such discrepancies and reveals both visual realism and semantic consistency.
  arXiv  Detail & Related papers  (2021-07-06T15:27:00Z)
• Mining Feature Relationships in Data [0.0]
  Feature relationship mining (FRM) uses a genetic programming approach to automatically discover symbolic relationships between continuous or categorical features in data. Our proposed approach is the first such symbolic approach with the goal of explicitly discovering relationships between features. Empirical testing on a variety of real-world datasets shows the proposed method is able to find high-quality, simple feature relationships.
  arXiv  Detail & Related papers  (2021-02-02T07:06:16Z)
• Improving Text Relationship Modeling with Artificial Data [0.07614628596146598]
  We apply and evaluate a synthetic data approach to relationship classification in digital libraries. We find that for classification on whole-part relationships between books, synthetic data improves a deep neural network classifier by 91%.
  arXiv  Detail & Related papers  (2020-10-27T22:04:54Z)
• Relation-Guided Representation Learning [53.60351496449232]
  We propose a new representation learning method that explicitly models and leverages sample relations. Our framework well preserves the relations between samples. By seeking to embed samples into subspace, we show that our method can address the large-scale and out-of-sample problem.
  arXiv  Detail & Related papers  (2020-07-11T10:57:45Z)
• Discovering Nonlinear Relations with Minimum Predictive Information Regularization [67.7764810514585]
  We introduce a novel minimum predictive information regularization method to infer directional relations from time series. Our method substantially outperforms other methods for learning nonlinear relations in synthetic datasets.
  arXiv  Detail & Related papers  (2020-01-07T04:28:00Z)

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.