RT info:eu-repo/semantics/conferenceObject
T1 Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes
A1 Prenkaj, Bardh
A1 Villaizán Vallelado, Mario
A1 Leemann, Tobias
A1 Kasneci, Gjergji
K1 Explicabilidad contrafactual gráfica
K1 Explicabilidad dinámica
K1 Explicaciones dependientes del tiempo
AB We introduce a novel semi-supervised Graph Counterfactual Explainer (GCE) methodology, Dynamic GRAph Counterfactual Explainer (DyGRACE). It leverages initial knowledge about the data distribution to search for valid counterfactuals while avoiding using information from potentially outdated decision functions in subsequent time steps. Employing two graph autoencoders (GAEs), DyGRACE learns the representation of each class in a binary classification scenario. The GAEs minimise the reconstruction error between the original graph and its learned representation during training. The method involves (i) optimising a parametric density function (implemented as a logistic regression function) to identify counterfactuals by maximising the factual autoencoder’s reconstruction error, (ii) minimising the counterfactual autoencoder’s error, and (iii) maximising the similarity between the factual and counterfactual graphs. This semi-supervised approach is independent of an underlying black-box oracle. A logistic regression model is trained on a set of graph pairs to learn weights that aid in finding counterfactuals. At inference, for each unseen graph, the logistic regressor identifies the best counterfactual candidate using these learned weights, while the GAEs can be iteratively updated to represent the continual adaptation of the learned graph representation over iterations. DyGRACE is quite effective and can act as a drift detector, identifying distributional drift based on differences in reconstruction errors between iterations. It avoids reliance on the oracle’s predictions in successive iterations, thereby increasing the efficiency of counterfactual discovery. DyGRACE, with its capacity for contrastive learning and drift detection, will offer new avenues for semi-supervised learning and explanation generation.
PB Springer Science and Business Media Deutschland GmbH
SN 9783031746291
YR 2025
FD 2025
LK https://uvadoc.uva.es/handle/10324/78814
UL https://uvadoc.uva.es/handle/10324/78814
LA eng
NO Meo, Rosa y Silvestri, Fabrizio. Machine Learning and Principles and Practice of Knowledge Discovery in Databases International Workshops of ECML PKDD 2023. Turín, 2025, p. 325-337.
NO Producción Científica
DS UVaDOC
RD 21-oct-2025