# Fidelity-Aware Recommendation Explanations via Stochastic Path Integration

arXiv: https://arxiv.org/abs/2511.18047 · HTML: https://mlsanity.com/paper/2511.18047/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 53 references that are in the map.
- First posted on arXiv 22 Nov 2025.

## Builds on (most cited first, 24 of 24)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Variational Autoencoders for Collaborative Filtering](https://mlsanity.com/paper/1802.05814/) (2018)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [OpenXAI: Towards a Transparent Evaluation of Model Explanations](https://mlsanity.com/paper/2206.11104/) (2022)
- [Guided Integrated Gradients: An Adaptive Path Method for Removing Noise](https://mlsanity.com/paper/2106.09788/) (2021)
- [RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback](https://mlsanity.com/paper/1912.11160/) (2019)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [On Baselines for Local Feature Attributions](https://mlsanity.com/paper/2101.00905/) (2021)
- [Counterfactual Explanations for Neural Recommenders](https://mlsanity.com/paper/2105.05008/) (2021)
- [Revisiting the Performance of iALS on Item Recommendation Benchmarks](https://mlsanity.com/paper/2110.14037/) (2021)
- [Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering](https://mlsanity.com/paper/2010.07042/) (2020)
- [Explaining Latent Factor Models for Recommendation with Influence Functions](https://mlsanity.com/paper/1811.08120/) (2018)
- [Neural Attentive Multiview Machines](https://mlsanity.com/paper/2002.07696/) (2020)
- [Cold Item Integration in Deep Hybrid Recommenders via Tunable Stochastic Gates](https://mlsanity.com/paper/2112.07615/) (2021)
- [BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation](https://mlsanity.com/paper/2412.17512/) (2024)
- [Hierarchical Matrix Factorization for Interpretable Collaborative Filtering](https://mlsanity.com/paper/2311.13277/) (2023)

## Built on by (most cited first, 3 of 3)

- [Concept-Guided Fine-Tuning: Steering ViTs away from Spurious Correlations to Improve Robustness](https://mlsanity.com/paper/2603.08309/) (2026)
- [Why This, Not That? Mining User Profiles for Pair-wise Counterfactuals](https://mlsanity.com/paper/2608.21662/) (2026)
- [ConEx: Human-Interpretable Saliency Maps via Concept-Aware Attribution](https://mlsanity.com/paper/2610.04605/) (2026)

## Abstract (arXiv)

Explanation fidelity, which measures how accurately an explanation reflects a model's true reasoning, remains critically underexplored in recommender systems. We introduce SPINRec (Stochastic Path Integration for Neural Recommender Explanations), a model-agnostic approach that adapts path-integration techniques to the sparse and implicit nature of recommendation data. To overcome the limitations of prior methods, SPINRec employs stochastic baseline sampling: instead of integrating from a fixed or unrealistic baseline, it samples multiple plausible user profiles from the empirical data distribution and selects the most faithful attribution path. This design captures the influence of both observed and unobserved interactions, yielding more stable and personalized explanations. We conduct the most comprehensive fidelity evaluation to date across three models (MF, VAE, NCF), three datasets (ML1M, Yahoo! Music, Pinterest), and a suite of counterfactual metrics, including AUC-based perturbation curves and fixed-length diagnostics. SPINRec consistently outperforms all baselines, establishing a new benchmark for faithful explainability in recommendation. Code and evaluation tools are publicly available at https://github.com/DeltaLabTLV/SPINRec.