Michael Müller, MSc.

@inproceedings{10.1145/3805712.3809584,
author = {Mohammadi, Amir Reza and Peintner, Andreas and M\"{u}ller, Michael M. and Zangerle, Eva},
title = {Minimal-Perturbation Counterfactuals through Guided Denoising Diffusion for Recommender Systems Explanation},
year = {2026},
isbn = {9798400725999},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3805712.3809584},
doi = {10.1145/3805712.3809584},
abstract = {Counterfactual explanations for recommender systems aim to identify minimal changes to a user's interaction history that would alter the model's recommendation, thereby providing actionable and user-centric explanations. However, existing CE methods often rely on local perturbation or mask-based strategies that require substantial profile modifications and exhibit unstable behavior under fine-grained ranking changes. In this work, we propose DiceRec, a diffusion-based, model-agnostic framework for generating interaction-level counterfactual explanations. DiceRec leverages denoising diffusion probabilistic models to learn the distribution of user interaction histories and integrates counterfactual objectives directly into the reverse diffusion process via guided denoising. By shaping the denoising trajectory at each step, DiceRec generates compact, semantically coherent counterfactuals that induce the desired ranking changes without relying on explicit sparsity regularization or heuristic perturbation budgets. Beyond the method itself, we introduce a fine-grained and constrained evaluation protocol that reveals important differences in explanation quality that are obscured by conventional coarse-grained, percentage-based perturbation schemes. Through extensive experiments, we show that DiceRec consistently outperforms state-of-the-art baselines, particularly in minimal-perturbation scenarios that reflect realistic counterfactual conditions. Our results highlight the advantages of diffusion-based counterfactual generation and underscore the necessity of fine-grained evaluation for faithful explanation assessment in recommender systems.},
booktitle = {Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval},
pages = {1371–1381},
numpages = {11},
keywords = {recommender systems, counterfactual explanation, denoising diffusion probabilistic models, evaluation},
location = {Australia},
series = {SIGIR '26}
}

@inproceedings{10.1145/3774935.3806172,
author = {M\"{u}ller, Michael and Mohammadi, Amir Reza and Peintner, Andreas and Barroso Gstrein, Beatriz and Specht, G\"{u}nther and Zangerle, Eva},
title = {Can Third-Party Annotators Reliably Evaluate Conversational Recommender Systems?},
year = {2026},
isbn = {9798400723117},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3774935.3806172},
doi = {10.1145/3774935.3806172},
abstract = {User-centric evaluation has become a key paradigm for assessing Conversational Recommender Systems (CRS), aiming to capture subjective qualities such as satisfaction, trust, and rapport. To enable scalable evaluation, recent work increasingly relies on third-party annotations of static dialogue logs by crowd workers or large language models. However, the reliability of this practice remains largely unexamined. In this paper, we present a large-scale empirical study investigating the reliability and structure of user-centric CRS evaluation on static dialogue transcripts. We collected 1,053 annotations from 124 crowd workers on 200 ReDial dialogues using the 18-dimensional CRS-Que framework. Using random-effects reliability models and correlation analysis, we quantify the stability of individual dimensions and their interdependencies. Our results show that utilitarian and outcome-oriented dimensions such as accuracy, usefulness, and satisfaction achieve moderate reliability under aggregation, whereas socially grounded constructs such as humanness and rapport are substantially less reliable. Furthermore, many dimensions collapse into a single global quality signal, revealing a strong halo effect in third-party judgments. These findings challenge the validity of single-annotator and LLM-based evaluation protocols and motivate the need for multi-rater aggregation and dimension reduction in offline CRS evaluation.},
booktitle = {Proceedings of the 34th ACM Conference on User Modeling, Adaptation and Personalization},
pages = {351–355},
numpages = {5},
keywords = {Conversational Recommender Systems, User-Centric, Evaluation, User Interaction, Personalization},
location = {
},
series = {UMAP '26}
}

@article{mohammadi2025quantitative,
  title={Yearning for Better Metrics: Revisiting the ReDial Dataset for Evaluating Conversational Recommender Systems},
  author={M{\"u}ller, Michael M and Mohammadi, Amir Reza and Peintner, Andreas and Gstrein, Beatriz Barroso and Zangerle, Eva and Specht, G{\"u}nther},
  year={2025},
  booktitle={Proceedings of the 36th GI-Workshop Grundlagen von Datenbanken (GvDB'25), Regensburg, Germany},
}

@article{mohammadi2025quantitative,
  title={Quantitative Assessment of GNN Counterfactual Explanation Robustness and Reproducibility under Adversarial Influence},
  author={Mohammadi, Amir Reza and M{\"u}ller, Michael M and Peintner, Andreas and Gstrein, Beatriz Barroso and Zangerle, Eva and Specht, G{\"u}nther},
  year={2025},
  booktitle    = {Proceedings of the 36th GI-Workshop Grundlagen von Datenbanken (GvDB'25), Regensburg, Germany},
}

@inproceedings{mohammadi:recsys:2025,
author = {Mohammadi, Amir Reza and Peintner, Andreas and M\"{u}ller, Michael and Zangerle, Eva},
title = {Beyond Top-1: Addressing Inconsistencies in Evaluating Counterfactual Explanations for Recommender Systems},
year = {2025},
isbn = {9798400713644},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3705328.3748028},
doi = {10.1145/3705328.3748028},
abstract = {Explainability in recommender systems (RS) remains a pivotal yet challenging research frontier. Among state-of-the-art techniques, counterfactual explanations stand out for their effectiveness, as they show how small changes to input data can alter recommendations, providing actionable insights that build user trust and enhance transparency. Despite their growing prominence, the evaluation of counterfactual explanations in RS is far from standardized. Specifically, existing metrics show inconsistency since they are affected by variations in the performance of the underlying recommenders. Hence, we critically examine the evaluation of counterfactual explainers through consistency as the key principle of effective evaluation. Through extensive experiments, we assess how going beyond top-1 recommendation and incorporating top-k recommendations impacts the consistency of existing evaluation metrics. Our findings reveal factors that impact the consistency of existing evaluation metrics and offer a step toward effectively mitigating the inconsistency problem in counterfactual explanation evaluation.},
booktitle = {Proceedings of the Nineteenth ACM Conference on Recommender Systems},
pages = {515–520},
numpages = {6},
keywords = {Recommender Systems, Counterfactual Explanation, Evaluation},
location = {
},
series = {RecSys '25}
}

@inproceedings{peintner2025hyperhawkes,
  author       = {Andreas Peintner and
                  Amir Reza Mohammadi and
                  Michael M{\"{u}}ller and
                  Eva Zangerle},
  title        = {Hypergraph-based Temporal Modelling of Repeated Intent for Sequential
                  Recommendation},
  booktitle    = {Proceedings of the {ACM} on Web Conference 2025, {WWW} 2025, Sydney,
                  NSW, Australia, 28 April 2025- 2 May 2025},
  pages        = {3809--3818},
  publisher    = {{ACM}},
  year         = {2025},
  url          = {https://doi.org/10.1145/3696410.3714896},
  doi          = {10.1145/3696410.3714896}
}

@InProceedings{murauer2022dtgrams,
  author       = {Michael M. M{\"{u}}ller and
                  G{\"{u}}nther Specht and
                  Lukas Kleinheinz and
                  Janette F. Walde},
  booktitle = {Proceedings of the 35nd GI-Workshop Grundlagen von Datenbanksysteme (GvDB'24) },
  title        = {Bias Correction and Machine Learning in {AR(1)} Estimation: Bridging
                  Traditional and Modern Techniques},
  year      = {2024},
}