About Me
Welcome! I am Felice Antonio Merra an Applied Scientist II at Amazon.com working on Information Retrieval, Recommender Systems and Netural Language Processing for Amazon Search.
I graduated as Ph.D. cum laude defending a Ph.D. Thesis on Adversarial Machine Learning in Recommender Systems at Department of Electrical Engineering and Information Technology, Polytechnic University of Bari @PolibaOfficial supervised by Prof. Tommaso Di Noia.
I did a Summer Internship as Applied Scientist at Amazon.com in the Amazon Search and Personalization Team, and a research Visiting at Knowledge Media Institute under the supervision of Prof. Enrico Motta.
Email: merrafelice@gmail.com
Important News
- [Highlight] Paper accepted at SIGIR 2023 on a defense strategies for recommender systems. Announcement
- [Highlight] Paper accepted at WWW 2023 on improvements for e-commerce applications. Paper
- [Highlight] Ph.D. Graduation cum Laude. Slides
- [Highlight] Best Short Paper - Runner Up: A Formal Analysis of Recommendation Quality of Adversarially-trained Recommenders at CIKM 2021
- [Highlight] MIT-IBM Watson AI Lab best paper award: Understanding the Effects of Adversarial Personalized Ranking Optimization Method on Recommendation Quality at AdvML@KDD 2021
Research Interest
My research activities mainly focus on artificial intelligence (AI). My investigation is devoted to novel approaches and applying machine learning (ML) algorithms, particularly to Trustworthy AI. In particular, I devote my attention to recommender system (RS) applications to study the robustness of modern ML recommender models affected by adversarial threats.
After having assessed the state-of-the-art of AML techniques in RS, I am invetsigating three main areas of study:
- the robustness of recommender models when affected by hand-engineered shilling attacks,
- the formal study of the effects of AML training strategies on the beyond-accuracy effects of recommenders, i.e., bias disparity, fairness, novelty
- the proposal of adversarial attacks against multimedia retrieval models.
- the Trustworthiness of ML (security, explainability, privacy, fairness, bias)
In the future, I plan to extend the previous line of study and continue to investigate AML approaches on other ML tasks, e.g., computer vision and reinforcement learning, with the aim to bridge the final users’ at the core of my research to verify how much they can Trust an ML system.
For more information you can look at my Curriculum Vitae.
Publications
Authors in alphabetical order. Bold style means Main Author.
2023
Felice Antonio Merra, Vito Walter Anelli, Tommaso DI Noia, Daniele Malitesta, Alberto Macino, Denoise to protect: a method to robustify visual recommenders from adversaries The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, Taipei, Taiwan (SIGIR 2023).
Felice Antonio Merra, Omar Zaidan, Fabricio de Soursa Nascimento, Improving the Relevance of Product Search for Queries with Negations, The 32nd Web Conference 2023, Austin, Texas (WWW 2023).
2022
Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra, Adversarial Recommender Systems: Attack, Defense, and Advances, The 3rd Edition of the Recommender Systems Handbook.
Jacek Golebiowski, Felice Antonio Merra, Ziawasch Abedjan, Felix Biessmann, Search Filter Ranking with Language-Aware Label Embeddings, TheWebConf 2022
Vito Walter Anelli, Alejandro Bellogin, Tommaso Di Noia, Francesco Donini, Antonio Ferrara, Daniele Malitesta, Felice Antonio Merra, Claudio Pomo,The challenging reproducibility task in Recommender Systems research between traditional and Deep Learning models, SEBD 2022
Yashar Deldjoo; Tommaso Di Noia; Daniele Malitesta; Felice Antonio Merra, Leveraging Content-Style Item Representation for Visual Recommendation, ECIR 2022
Vito Walter Anelli, Alejandro Bellogin, Tommaso Di Noia, Francesco Donini, Antonio Ferrara, Daniele Malitesta, Felice Antonio Merra, Claudio Pomo, V-Elliot: Speeding up Visual Recommendation via a GPU-powered Data Input Pipeline, NVIDIA GTC 2022
2021
Vito Walter Anelli; Yashar Deldjoo; Tommaso Di Noia; Felice Antonio Merra, A Formal Analysis of Recommendation Quality of Adversarially-trained Recommenders, CIKM 2021
Vito Walter Anelli; Tommaso Di Noia; Felice Antonio Merra, The Idiosyncratic Effects of Adversarial Training on Bias in Personalized Recommendation Learning, RecSys 2021
Vito Walter Anelli, Alejandro Bellogin, Tommaso Di Noia, Francesco Donini, Antonio Ferrara, Daniele Malitesta, Felice Antonio Merra, Claudio Pomo, V-Elliot: Build, Evaluate and Tune Visual Recommender Systems, RecSys 2021
Vito Walter Anelli , Tommaso Di Noia, Eugenio Di Sciascio, Daniele Malitesta and Felice Antonio Merra, Adversarial Attacks against Visual Recommendation: an Investigation on the Influence of Items’ Popularity, OHARS@RecSys2021
Vito Walter Anelli; Yashar Deldjoo; Tommaso Di Noia; Felice Antonio Merra, Understanding the Effects of Adversarial Personalized Ranking Optimization Method on Recommendation Quality, 3rd Workshop on Adversarial Learning Methods for Machine Learning and Data Mining @ KDD 2021 (virtual workshop)
Yashar Deldjoo, Tommaso Di Noia, Eugenio Di Sciascio, Felice Antonio Merra, A Regression Framework to Interpret the Robustness of Recommender Systems Against Shilling Attacks, IIR 2021
Vito Walter Anelli, Alejandro Bellogin, Tommaso Di Noia, Francesco Donini, Antonio Ferrara, Daniele Malitesta, Felice Antonio Merra, Claudio Pomo, How to perform reproducible experiments in the ELLIOT recommendation framework: data processing, model selection, and performance evaluation, IIR 2021
Giuseppe De Candia, Tommaso Di Noia, Eugenio Di Sciascio, Felice Antonio Merra, AMFLP: Adversarial Matrix Factorization-based Link Predictor in Social Graphs, SEBD 2021.
Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Daniele Malitesta, Felice Antonio Merra, A Study of Defensive Methods to Protect Visual Recommendation Against Adversarial Manipulation of Images,The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
Vito Walter Anelli, Alejandro Bellogin, Tommaso Di Noia, Francesco Donini, Antonio Ferrara, Daniele Malitesta, Felice Antonio Merra, Claudio Pomo, Elliot: a Comprehensive and Rigorous Framework for Reproducible Recommender Systems Evaluation,The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval
Yashar Deldjoo, Tommaso Di Noia, Daniele Malitesta, Felice Antonio Merra, A Study on the Relative Importance of Convolutional Neural Networks in Visually-Aware Recommender Systems ,The 4th CVPR Workshop on Computer Vision for Fashion, Art, and Design
Vito Walter Anelli, Alejandro Bellogin, Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra. MSAP: Multi-Step Adversarial Perturbations on Recommender Systems Embeddings, FLAIRS 2021
Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra, A survey on Adversarial Recommender Systems: from Attack/Defense strategies to Generative Adversarial Networks, ACM Computing Surveys, March 2021
2020
Vito Walter Anelli, Tommaso Di Noia, Daniele Malitesta, Felice Antonio Merra, Assessing Perceptual and Recommendation Mutation of Adversarially-Poisoned Visual Recommenders, WSCD@NeurIPS2020, The 1st Workshop on Dataset Curation and Security co-located with the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada (Virtual Event) Code.
Vito Walter Anelli, Tommaso Di Noia, Daniele Malitesta, Felice Antonio Merra, An Empirical Study of DNNs Robustification Inefficacy in Protecting Visual Recommenders, arXiv.
Vito Walter Anelli, Alejandro Bellogín, Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra, Multi-Step Adversarial Perturbations on Recommender Systems Embeddings , arXiv.
Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra, Adversarial Learning for Recommendation: Applications for Security and Generative Tasks - Concept to Code, To appear in Proceedings of the 14th ACM Conference on Recommender Systems, RecSys 2020, Virtual Conference (Brazil).
Yashar Deldjoo, Tommaso Di Noia, Eugenio Di Sciascio, Felice Antonio Merra, How Dataset Characteristics Affect the Robustness of Collaborative Recommendation Models, SIGIR 2020. X’ian, China, July, 2020. Video
Tommaso Di Noia, Daniele Malitesta, Felice Antonio Merra, TAaMR: Targeted Adversarial Attack against Multimedia Recommender Systems, The 3rd International Workshop on Dependable and Secure Machine Learning – DSML 2020 Co-located with the 50th IEEE/IFIP International Conference on Dependable Systems and Networks (DSN 2020). Code Video
Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra, Eugenio Di Sciascio, Giuseppe Acciani, Knowledge-enhanced Shilling Attacks for recommendation, To appear in Proceedings of the 28th Italian Symposium on Advanced Database Systems, June 21-24, 2020 - Villasimius, Sardinia, Italy
Vito Walter Anelli, Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra, Eugenio Di Sciascio, SAShA: Semantic-Aware Shilling Attacks on Recommender Systems exploiting Knowledge Graphs, The 17th Extended Semantic Web Conference. Springer, Cham., Heraklion, Greece, May 31- June 4, 2020. Video
Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra, Adversarial Machine Learning in Recommender Systems, Slide, The 13th ACM International WSDM Conference, Texas, February 3-7, 2020.
2019
Yashar Deldjoo, Tommaso Di Noia, Felice Antonio Merra, Assessing Knowledge-enhanced Shilling Attacks for recommendation the Impact of a User-Item Collaborative Attack on Class of Users, Slide , InProceedings of the 1stWorkshop on the Impact of Recommender Systems co-located with 13th ACM Con-ference on Recommender Systems, ImpactRS@RecSys 2019, Copenhag InProceedings of the 1stWorkshop on the Impact of Recommender Systems co-located with 13th ACM Con-ference on Recommender Systems, ImpactRS@RecSys 2019, Copenhagen, Denmark, September 19, 2019.