arXiv subjects

Pouya Khani

Publications and source records attributed to Pouya Khani.

4 recordsLinked to original sources

arXiv2026

Incremental Delta-Shapley: A Standalone Runtime for Predicate Attribution on Sliding Windows

Continuous aggregate queries over sliding windows are common in real-time analytics, but most systems report \emph{what} an aggregate is doing without attributing \emph{which} predicates account for the result. A companion paper~\cite{khani2026closedformpredicatelevelshapleyattribution} shows that exact predicate-level Shapley attribution for SUM, COUNT, AVG, and variance needs only three additive predicate summaries with closed-form coefficients. Those results settle the mathematics, not how a runtime maintains summaries across slides, exposes attribution, answers unregistered predicates, or amortizes repeated ad hoc ones. We present \textbf{IDS} (Incremental Delta-Shapley), a standalone single-node runtime that turns those closed forms into a deployable explanation system. IDS consumes window-maintenance deltas, updates global, marginal, and atom summaries, and evaluates any closed form in constant time. Overlapping predicates use atomic refinement, and a restricted SQL-like API exposes attribution and its per-slide change as first-class operators. Unregistered predicates are answered by a retained-state scan, an inverted index, or an amortized sliding-window sample with concentration guarantees; frequent ones are promoted by rebuilding the refinement. On synthetic, adversarial, NEXMark-style, and NYC taxi workloads, attribution matches exhaustive Shapley enumeration to floating-point precision; incremental maintenance is flat in $N$ and up to $4.3\times10^{5}\times$ faster than per-window scans of the same form; and adaptive promotion cuts ad hoc cost by up to $9.2\times$ on Zipfian traces.

cs.DB↗

arXiv2026

Closed-Form Predicate-Level Shapley Attribution for Sliding-Window Aggregates

Streaming engines report sliding-window aggregates in real time, but they do not explain \emph{why} an aggregate takes its current value. A natural target is the Shapley value from cooperative game theory, which axiomatically distributes an aggregate among the tuples in the window. Practitioners, however, ask predicate-level questions (e.g., how much a region or customer tier contributed to an average or variance spike). Exact Shapley computation is exponential in the window size, and existing estimators discard the massive overlap between consecutive windows. We show that for SUM, COUNT, AVG, and population/sample variance, exact predicate-level Shapley values admit closed forms in three additively maintained summaries per predicate (count, sum, and sum of squares), with coefficients that depend only on two running harmonic numbers. Attribution therefore reduces to $O(1)$ summary updates per slide for registered predicates, with no coalition enumeration. Overlapping and compositional predicates are answered exactly via atomic refinement of Boolean signatures. We further characterize the phenomenon: every moment-polynomial aggregate admits such a form, while MAX, MIN, and quantiles provably do not at any fixed moment order. Experiments match brute-force Shapley values to floating-point precision on over $10{,}000$ windows, sustain $\approx\!2\,\mu$s per slide up to $N=10^6$ ($3{,}200\times$ faster than per-window recomputation of the same formulas), and explain a nighttime fare spike on 2.9M NYC taxi trips at $\approx\!1.8$M summary updates per second.

cs.DB↗

arXiv2024

IBO: Inpainting-Based Occlusion to Enhance Explainable Artificial Intelligence Evaluation in Histopathology

Histopathological image analysis is crucial for accurate cancer diagnosis and treatment planning. While deep learning models, especially convolutional neural networks, have advanced this field, their "black-box" nature raises concerns about interpretability and trustworthiness. Explainable Artificial Intelligence (XAI) techniques aim to address these concerns, but evaluating their effectiveness remains challenging. A significant issue with current occlusion-based XAI methods is that they often generate Out-of-Distribution (OoD) samples, leading to inaccurate evaluations. In this paper, we introduce Inpainting-Based Occlusion (IBO), a novel occlusion strategy that utilizes a Denoising Diffusion Probabilistic Model to inpaint occluded regions in histopathological images. By replacing cancerous areas with realistic, non-cancerous tissue, IBO minimizes OoD artifacts and preserves data integrity. We evaluate our method on the CAMELYON16 dataset through two phases: first, by assessing perceptual similarity using the Learned Perceptual Image Patch Similarity (LPIPS) metric, and second, by quantifying the impact on model predictions through Area Under the Curve (AUC) analysis. Our results demonstrate that IBO significantly improves perceptual fidelity, achieving nearly twice the improvement in LPIPS scores compared to the best existing occlusion strategy. Additionally, IBO increased the precision of XAI performance prediction from 42% to 71% compared to traditional methods. These results demonstrate IBO's potential to provide more reliable evaluations of XAI techniques, benefiting histopathology and other applications. The source code for this study is available at https://github.com/a-fsh-r/IBO.

cs.CV↗

arXiv2023

TbExplain: A Text-based Explanation Method for Scene Classification Models with the Statistical Prediction Correction

The field of Explainable Artificial Intelligence (XAI) aims to improve the interpretability of black-box machine learning models. Building a heatmap based on the importance value of input features is a popular method for explaining the underlying functions of such models in producing their predictions. Heatmaps are almost understandable to humans, yet they are not without flaws. Non-expert users, for example, may not fully understand the logic of heatmaps (the logic in which relevant pixels to the model's prediction are highlighted with different intensities or colors). Additionally, objects and regions of the input image that are relevant to the model prediction are frequently not entirely differentiated by heatmaps. In this paper, we propose a framework called TbExplain that employs XAI techniques and a pre-trained object detector to present text-based explanations of scene classification models. Moreover, TbExplain incorporates a novel method to correct predictions and textually explain them based on the statistics of objects in the input image when the initial prediction is unreliable. To assess the trustworthiness and validity of the text-based explanations, we conducted a qualitative experiment, and the findings indicated that these explanations are sufficiently reliable. Furthermore, our quantitative and qualitative experiments on TbExplain with scene classification datasets reveal an improvement in classification accuracy over ResNet variants.

cs.CV↗