Felice Antonio Merra

Felice Antonio Merra

Auto-generated profile, based on publicly available information

Felice Antonio Merra

Cognism, Bari, Italy

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 March 2025 in ACM Transactions on Recommender Systems
Verified
Journal Article
Open access
DMDaniele Malitesta
Daniele Malitesta
GCGiandomenico Cornacchia
Giandomenico Cornacchia
CPClaudio Pomo
Claudio Pomo
FMFelice Antonio Merra
Felice Antonio Merra
TNTommaso Di Noia
Tommaso Di Noia
ESEugenio Di Sciascio
Eugenio Di Sciascio
Recommender systems (RSs) provide customers with a personalized navigation experience within the vast catalogs of products and services offered on popular online platforms. Despite the substantial success of traditional RSs, recommendation remains a highly challenging task, especially in specific scenarios and domains. For example, human affinity for items described through multimedia content (e.g., images, audio, and text), such as fashion products, movies, and music, is multi-faceted and primarily driven by their diverse characteristics. Therefore, by leveraging all available signals in such scenarios, multimodality enables us to tap into richer information sources and construct more refined user/item profiles for recommendations. Despite the growing number of multimodal techniques proposed for multimedia recommendation, the existing literature lacks a shared and universal schema for modeling and solving the recommendation problem through the lens of multimodality. Given the recent advances in multimodal deep learning for other tasks and scenarios where precise theoretical and applicative procedures exist, we also consider it imperative to formalize a general multimodal schema for multimedia recommendation. In this work, we first provide a comprehensive literature review of multimodal approaches for multimedia recommendation from the last eight years. Second, we outline the theoretical foundations of a multimodal pipeline for multimedia recommendation by identifying and formally organizing recurring solutions/patterns; at the same time, we demonstrate its rationale by conceptually applying it to selected state-of-the-art approaches in multimedia recommendation. Third, we conduct a benchmarking analysis of recent algorithms for multimedia recommendation within Elliot, a rigorous framework for evaluating recommender systems, where we re-implement such multimedia recommendation approaches. Finally, we highlight the significant unresolved challenges in multimodal deep learning for multimedia recommendation and suggest possible avenues for addressing them. The primary aim of this work is to provide guidelines for designing and implementing the next generation of multimodal approaches in multimedia recommendation.

13 July 2025
Verified
Conference Paper
Open access
DPDario Di Palma
Dario Di Palma
FMFelice Antonio Merra
Felice Antonio Merra
MSMaurizio Sfilio
Maurizio Sfilio
Vito Walter AnelliVito Walter Anelli
Vito Walter Anelli
FNFedelucio Narducci
Fedelucio Narducci
TNTommaso Di Noia
Tommaso Di Noia

18 July 2023
Verified
Conference Paper
Open access
FMFelice Antonio Merra
Felice Antonio Merra
Vito Walter AnelliVito Walter Anelli
Vito Walter Anelli
TNTommaso Di Noia
Tommaso Di Noia
DMDaniele Malitesta
Daniele Malitesta
AMAlberto Carlo Maria Mancino
Alberto Carlo Maria Mancino
While the integration of product images enhances the recommendation performance of visual-based recommender systems (VRSs), this can make the model vulnerable to adversaries that can produce noised images capable to alter the recommendation behavior. Recently, stronger and stronger adversarial attacks have emerged to raise awareness of these risks; however, effective defense methods are still an urgent open challenge. In this work, we propose "Adversarial Image Denoiser" (AiD), a novel defense method that cleans up the item images by malicious perturbations. In particular, we design a training strategy whose denoising objective is to minimize both the visual differences between clean and adversarial images and preserve the ranking performance in authentic settings. We perform experiments to evaluate the efficacy of AiD using three state-of-the-art adversarial attacks mounted against standard VRSs. Code and datasets at https://github.com/sisinflab/Denoise-to-protect-VRS.

10 November 2025
Verified
Conference Paper
Open access
FMFelice Antonio Merra
Felice Antonio Merra
KSKristian Skračić
Kristian Skračić
DMDaniele Malitesta
Daniele Malitesta
JGJacek Golebiowski
Jacek Golebiowski
PMPasquale Minervini
Pasquale Minervini

30 April 2023
Verified
Conference Paper
Open access
FMFelice Antonio Merra
Felice Antonio Merra
OZOmar Zaidan
Omar Zaidan
FNFabricio de Sousa Nascimento
Fabricio de Sousa Nascimento
Product search engines (PSEs) play an essential role in retail websites as they make it easier for users to retrieve relevant products within large catalogs. Despite the continuous progress that has led to increasingly accurate search engines, a limited focus has been given to their performance on queries with negations. Indeed, while we would expect to retrieve different products for the queries “iPhone 13 cover with ring” and “iPhone 13 cover without ring”, this does not happen in popular PSEs with the latter query containing results with the unwanted ring component. The limitation of modern PSEs in understanding negations motivates the need for further investigation. In this work, we start by defining the negation intent in users queries. Then, we design a transformer-based model, named Negation Detector for Queries (ND4Q), that reaches optimal performance in negation detection (+95% on accuracy metrics). Finally, having built the first negation detector for product search queries, we propose a negation-aware filtering strategy, named Filtering Irrelevant Products (FIP). The promising experimental results in improve the PSE relevance performance using FIP (+9.41% on [email protected] for queries where the negation starts with "without") pave the way to additional research effort towards negation-aware PSEs.