FMMO: Detecting the Divergence Between Local Attribution and Global Drift

• URL: http://arxiv.org/abs/2609.06173v1
• Date: Sat, 05 Sep 2026 16:25:59 GMT
• Title: FMMO: Detecting the Divergence Between Local Attribution and Global Drift
• Abstract summary: Post-deployment drift poses a critical risk to algorithmic accountability.<n>We demonstrate that popular local attribution methods can exhibit misleading stability even as model reliability collapses.<n>We propose a Framework for Model Monitoring and Observability (FMMO) designed to expose the divergence between local explanation stability and global distribution shifts.
• Score: 2.007262412327553
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Post-deployment drift poses a critical risk to algorithmic accountability, particularly when ground truth labels are delayed and performance degradation becomes a "silent failure". While Explainable AI (XAI) is often relied upon to audit these shifts, we demonstrate that popular local attribution methods (e.g., TreeSHAP) can exhibit misleading stability even as model reliability collapses. In this paper, we propose a Framework for Model Monitoring and Observability (FMMO) designed to expose the divergence between local explanation stability and global distribution shifts. Using benchmark, synthetic, and real-world datasets, we show that local XAI methods fail to flag drift-induced disparate impact, specifically where False Positive Rates spike for protected groups while feature attributions remain unchanged. By integrating global surrogate models with model utilization measurements, FMMO mitigates this fairness blind spot, ensuring that stakeholders can detect discriminatory deterioration that standard local XAI tools overlook.

Related papers

• Where World Models Break: Natural-Input Failure Discovery [13.330611636170103]
  We formalize the natural-input failure discovery problem, finding environment-valid conditions and action prefixes that induce severe prediction risk.<n>We propose BasinLens, which exploits the underlying structure of valid inputs, by pairing uncertainty-guided global search with typed local replacements.
  arXiv  Detail & Related papers  (2026-08-23T13:53:15Z)
• Localizing to Debias: A Patch-Level Benchmark and Baseline for Weakly Supervised Spatial Anomaly Detection [7.474723197425266]
  We propose a sparse-temporal framework that bridges temporal anomaly detection with fine-grained spatial localization.<n>SST-WSDLVA focuses on the most anomaly-relevant-temporal regions through dynamic sparsification.<n>We publicly release frame-level spatial annotations and a method-agnostic evaluation for three public datasets.
  arXiv  Detail & Related papers  (2026-08-12T13:27:20Z)
• Are Tabular Foundation Models Robust to Realistic Query Distribution Shifts in Microbiome Data? [2.4513329242158512]
  Tabular foundation models (TFMs) achieve strong performance on microbiome abundance data, yet their robustness under realistic distribution shift remains poorly characterized.<n>We introduce a benchmark that evaluates the robustness of TFMs to biologically inspired perturbations across six gut microbiome datasets spanning four disease contexts.
  arXiv  Detail & Related papers  (2026-06-23T15:52:35Z)
• Discovery of Hidden Miscalibration Regimes [52.452902154360565]
  Models may be systematically overconfident on some kinds of inputs and underconfident on others.<n>We define the corresponding miscalibration field and propose a diagnostic framework for estimating it.<n>Our approach learns a calibration-aware representation of the input space and estimates signed local miscalibration by kernel smoothing in the learned geometry.
  arXiv  Detail & Related papers  (2026-05-13T13:07:50Z)
• Learning Stable Predictors from Weak Supervision under Distribution Shift [2.8410059035029955]
  Learning from weak or proxy supervision is common when ground-truth labels are unavailable.<n>We formalize this as supervision drift, defined as changes in P(y | x, c) across contexts.<n>We study it in CRISPR-Cas13d experiments where guide efficacy is inferred indirectly from RNA-seq responses.
  arXiv  Detail & Related papers  (2026-04-05T23:46:49Z)
• RISE: Interactive Visual Diagnosis of Fairness in Machine Learning Models [3.409008933025072]
  We introduce textitRISE (Residual Inspection through Sorted Evaluation), an interactive visualization tool that converts sorted residuals into interpretable patterns.<n>By connecting residual curve structures to formal fairness notions, RISE enables localized disparity diagnosis, subgroup comparison across environments, and the detection of hidden fairness issues.
  arXiv  Detail & Related papers  (2026-02-04T09:01:21Z)
• Fair Deepfake Detectors Can Generalize [51.21167546843708]
  We show that controlling for confounders (data distribution and model capacity) enables improved generalization via fairness interventions.<n>Motivated by this insight, we propose Demographic Attribute-insensitive Intervention Detection (DAID), a plug-and-play framework composed of: i) Demographic-aware data rebalancing, which employs inverse-propensity weighting and subgroup-wise feature normalization to neutralize distributional biases; and ii) Demographic-agnostic feature aggregation, which uses a novel alignment loss to suppress sensitive-attribute signals.<n>DAID consistently achieves superior performance in both fairness and generalization compared to several state-of-the-art
  arXiv  Detail & Related papers  (2025-07-03T14:10:02Z)
• TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data [62.22804234013273]
  We propose a simple failure detection framework to unify and facilitate classification with rejection under both covariate and semantic shifts.<n>Our key insight is that by separating and consolidating failure-specific reliability knowledge with low-rank adapters, we can enhance the failure detection ability effectively and flexibly.
  arXiv  Detail & Related papers  (2025-04-20T09:20:55Z)
• Causal Disentanglement Hidden Markov Model for Fault Diagnosis [55.90917958154425]
  We propose a Causal Disentanglement Hidden Markov model (CDHM) to learn the causality in the bearing fault mechanism. Specifically, we make full use of the time-series data and progressively disentangle the vibration signal into fault-relevant and fault-irrelevant factors. To expand the scope of the application, we adopt unsupervised domain adaptation to transfer the learned disentangled representations to other working environments.
  arXiv  Detail & Related papers  (2023-08-06T05:58:45Z)
• Change Detection for Local Explainability in Evolving Data Streams [72.4816340552763]
  Local feature attribution methods have become a popular technique for post-hoc and model-agnostic explanations. It is often unclear how local attributions behave in realistic, constantly evolving settings such as streaming and online applications. We present CDLEEDS, a flexible and model-agnostic framework for detecting local change and concept drift.
  arXiv  Detail & Related papers  (2022-09-06T18:38:34Z)
• Tracking the risk of a deployed model and detecting harmful distribution shifts [105.27463615756733]
  In practice, it may make sense to ignore benign shifts, under which the performance of a deployed model does not degrade substantially. We argue that a sensible method for firing off a warning has to both (a) detect harmful shifts while ignoring benign ones, and (b) allow continuous monitoring of model performance without increasing the false alarm rate.
  arXiv  Detail & Related papers  (2021-10-12T17:21:41Z)

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.