analiza aiqbench
This research addresses the physical implausibility of standard counterfactual explanations in time-series data by operating within Empirical Mode Decomposition space rather than raw feature space. By substituting specific Intrinsic Mode Functions with those from a nearest unlike neighbor, IMFACT preserves temporal structure while reliably flipping classifier decisions on oscillatory signals like vibration and fruit fly movement patterns. The study demonstrates that variance-based IMF selection strategies combined with multi-neighbor cycling significantly outperform baseline techniques in reliability and proximity metrics for fault detection applications.
IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution
arXiv:2608.04777v1 Announce Type: new Abstract: Oscillatory signals, such as vibration, carry class-discriminative information in specific frequency bands; perturbing them in raw feature space for counterfactual analysis easily destroys their temporal structure and produces physically implausible results. In this work, we introduce IMFACT (IMF-based counterfACTuals), a model-agnostic framework for generating plausible counterfactual explanations for time series classifiers that operates in the decomposition space of Empirical Mode Decomposition. An input signal is split into Intrinsic Mode Functions (IMFs), and selected IMFs are progressively substituted with those of a Nearest Unlike Neighbour (NUN) until the classifier flips to the target class. We evaluate six IMF-selection strategies and a multi-NUN cycling extension on two UCR benchmarks (FaultDetectionA, FruitFlies). The variance-based strategy with three NUNs outperforms two prominent baseline techniques on reliability and plausibility metrics, while cycling across three NUNs yields the best proximity across both datasets.
Abstract:Oscillatory signals, such as vibration, carry class-discriminative information in specific frequency bands; perturbing them in raw feature space for counterfactual analysis easily destroys their temporal structure and produces physically implausible results. In this work, we introduce IMFACT (IMF-based counterfACTuals), a model-agnostic framework for generating plausible counterfactual explanations for time series classifiers that operates in the decomposition space of Empirical Mode Decomposition. An input signal is split into Intrinsic Mode Functions (IMFs), and selected IMFs are progressively substituted with those of a Nearest Unlike Neighbour (NUN) until the classifier flips to the target class. We evaluate six IMF-selection strategies and a multi-NUN cycling extension on two UCR benchmarks (FaultDetectionA, FruitFlies). The variance-based strategy with three NUNs outperforms two prominent baseline techniques on reliability and plausibility metrics, while cycling across three NUNs yields the best proximity across both datasets.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2608.04777 [cs.LG]
(or arXiv:2608.04777v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.04777 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 234 cuvinte
Subiecte conexe
Why do models task game?
AI Alignment Forum · 6 aug. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026
Deconfusing Corrigibility
AI Alignment Forum · 17 oct. 2026
Towards A Unified Information Bottleneck Framework for Time Series Explanations
arXiv · 27 aug. 2026