
Daniele MalitestaUniversity of Paris-Saclay · CentraleSupeléc
Daniele Malitesta
Doctor of Philosophy
About
52
Publications
7,134
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
371
Citations
Introduction
I'm a postdoc reseacher at CentraleSupélec (Université Paris-Saclay). I pursued a PhD in Electrical and Information Engineering at Politecnico di Bari. My research interests are: Graph Representation Learning, Multimedia Recommendation, Adversarial Machine Learning and Deep Learning.
Publications
Publications (52)
Thanks to the great interest posed by researchers and companies, recommendation systems became a cornerstone of machine learning applications. However, concerns have arisen recently about the need for reproducibility, making it challenging to identify suitable pipelines. Several frameworks have been proposed to improve reproducibility, covering the...
In specific domains like fashion, music, and movie recommendation, the multi-faceted features characterizing products and services may influence each customer on online selling platforms differently, paving the way to novel multimodal recommendation models that can learn from such multimodal content. According to the literature, the common multimod...
Item recommendation (the task of predicting if a user may interact with new items from the catalogue in a recommendation system) and link prediction (the task of identifying missing links in a knowledge graph) have long been regarded as distinct problems. In this work, we show that the item recommendation problem can be seen as an instance of the l...
Diffusion-based recommender systems have recently proven to outperform traditional generative recommendation approaches, such as variational autoencoders and generative adversarial networks. Nevertheless, the machine learning literature has raised several concerns regarding the possibility that diffusion models, while learning the distribution of d...
Recommender systems act as filtering algorithms to provide users with items that might meet their interests according to the expressed preferences and items' characteristics. As of today, the collaborative filtering paradigm, along with deep learning techniques to learn high-quality users' and items' representations, constitute the de facto standar...
The First International Workshop on Graph-Based Approaches in Information Retrieval (IRonGraphs 2024) was held as a physical (in-person) event on March 24, 2024, in conjunction with the 46th European Conference on Information Retrieval (ECIR 2024) in Glasgow (Scotland). The scientific program included paper, spotlight, and poster presentations. Two...
Not at all. In this work, we question this procedure, highlighting that it would further damage the pipeline of any multimodal recom-mender system. First, we show that the lack of (some) modalities is, in fact, a widely-diffused phenomenon in multimodal recommendation. Second, we propose a pipeline that imputes missing multi-modal features in recom...
Recently, graph neural networks (GNNs)-based recommender systems have encountered great success in recommendation. As the number of GNNs approaches rises, some works have started questioning the theoretical and empirical reasons behind their superior performance. Nevertheless, this investigation still disregards that GNNs treat the recommendation d...
Recommender systems (RSs) provide customers with a personalized navigation experience within the vast catalogs of products and services ofered on popular online platforms. Despite the substantial success of traditional RSs, recommendation remains a highly challenging task, especially in speciic scenarios and domains. For example, human ainity for i...
Multimodal recommender systems work by augmenting the representation of the products in the catalogue through multimodal features extracted from images, textual descriptions, or audio tracks characterising such products. Nevertheless, in real-world applications, only a limited percentage of products come with multimodal content to extract meaningfu...
In the dynamic field of information retrieval, the adoption of graph-based approaches has become a notable research trend. Fueled by the growing research on Knowledge Graphs and Graph Neural Networks, these approaches rooted in graph theory have shown significant promise in enhancing the effectiveness and relevance of information retrieval results....
In this work, we introduce Ducho 2.0, the latest stable version of our framework. Differently from Ducho, Ducho 2.0 offers a more personalized user experience with the definition and import of custom extraction models fine-tuned on specific tasks and datasets. Moreover, the new version is capable of extracting and processing features through multim...
Graph neural networks (GNNs) have gained prominence in recommendation systems in recent years. By representing the user-item matrix as a bipartite and undirected graph, GNNs have demonstrated their potential to capture short-and long-distance user-item interactions, thereby learning more accurate preference patterns than traditional recommendation...
Multimodal-aware recommender systems (MRSs) exploit multi-modal content (e.g., product images or descriptions) as items' side information to improve recommendation accuracy. While most of such methods rely on factorization models (e.g., MFBPR) as base architecture, it has been shown that MFBPR may be affected by popularity bias, meaning that it inh...
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 f...
Recommender systems (RSs) offer personalized navigation experiences on online platforms, but recommendation remains a challenging task, particularly in specific scenarios and domains. Multimodality can help tap into richer information sources and construct more refined user/item profiles for recommendations. However, existing literature lacks a sha...
The successful integration of graph neural networks into recommender systems (RSs) has led to a novel paradigm in collaborative filtering (CF), graph collaborative filtering (graph CF). By representing user-item data as an undirected, bipartite graph, graph CF utilizes short- and long-range connections to extract collaborative signals that yield mo...
In domains such as fashion, music, food, and micro-video recommendation, items' representation can be suitably enhanced through multimodal side information (extracted from images, texts, or audio). Multimodal-aware recommender systems (MRSs) refer to the family of RSs which integrates extracted multimodal items' features into the classical recommen...
The success of graph neural network-based models (GNNs) has significantly advanced recommender systems by effectively modeling users and items as a bipartite, undirected graph. However, many original graph-based works often adopt results from baseline papers without verifying their validity for the specific configuration under analysis. Our work ad...
In multimodal-aware recommendation, the extraction of meaningful multimodal features is at the basis of high-quality recommendations. Generally, each recommendation framework implements its multimodal extraction procedures with specific strategies and tools. This is limiting for two reasons: (i) different extraction strategies do not ease the inter...
Graph convolutional networks (GCNs) are taking over collaborative filtering-based recommendation. Their message-passing schema effectively distills the collaborative signal throughout the user-item graph by propagating informative content from neighbor to ego nodes. In this demonstration, we show how to run complete experimental pipelines with six...
To date, graph collaborative filtering (CF) strategies have been shown to outperform pure CF models in generating accurate recommendations. Nevertheless, recent works have raised concerns about fairness and potential biases in the recommendation landscape since unfair recommendations may harm the interests of Consumers and Producers (CP). Acknowled...
To date, graph collaborative filtering (CF) strategies have been shown to outperform pure CF models in generating accurate recommendations. Nevertheless, recent works have raised concerns about fairness and potential biases in the recommendation landscape since unfair recommendations may harm the interests of Consumers and Producers (CP). Acknowled...
Pre-trained CNN models are frequently employed for a variety of machine learning tasks, including visual recognition and recommendation. We are interested in examining the application of attacks generated by adversarial machine learning techniques to the vertical domain of fashion and retail products. Specifically, the present work focuses on the r...
Graph collaborative filtering approaches learn refined users' and items' node representations by iteratively aggregating the informative content (called messages) coming from neighbor nodes into each ego node. Unfortunately, not all interactions (i.e., graph edges) may be equally important to the users and items involved. As this indiscriminate mes...
Graph convolutional networks (GCNs) have recently been shown to improve the recommendation accuracy of collaborative filtering algorithms. Their message-passing schema refines user and item node representation by aggregating the informative content from the neighborhood. However, after multiple hops, noisy contributions can flatten the differences...
Pre-trained CNN models are frequently employed for a variety of machine learning tasks, including visual recognition and recommendation. We are interested in examining the application of attacks generated by adversarial machine learning techniques to the vertical domain of fashion and retail products. Specifically, the present work focuses on the r...
When customers’ choices may depend on the visual appearance of products (e.g., fashion), visually-aware recommender systems (VRSs) have been shown to provide more accurate preference predictions than pure collaborative models. To refine recommendations, recent VRSs have tried to recognize the influence of each item’s visual characteristic on users’...
When customers' choices may depend on the visual appearance of products (e.g., fashion), visually-aware recommender systems (VRSs) have shown to provide more accurate preference predictions than pure collaborative models. To refine recommendations, recent VRSs have tried to recognize the influence of each item's visual characteristic on users' pref...
Recommender Systems have shown to be an effective way to alleviate the over-choice problem and provide accurate and tailored recommendations. However, the impressive number of proposed recommendation algorithms, splitting strategies, evaluation protocols, metrics, and tasks, has made rigorous experimental evaluation particularly challenging. ELLIOT...
The paper introduces Visual-Elliot (V-Elliot), a reproducibility framework for Visual Recommendation systems (VRSs) based on Elliot. framework provides the widest set of VRSs compared to other recommendation frameworks in the literature (i.e., 6 state-of-the-art models which have been commonly employed as baselines in recent works). The framework p...
Visually-aware recommender systems (VRSs) integrate products' image features with historical users' feedback to enhance recommendation performance. Such models have shown to be very effective in different domains, ranging from fashion, food, to point-of-interest. However, test-time adversarial attack strategies have recently unveiled severe securit...
Recommender Systems have shown to be an effective way to alleviate the over-choice problem and provide accurate and tailored recommendations. However, the impressive number of proposed recommendation algorithms, splitting strategies, evaluation protocols, metrics, and tasks, has made rigorous experimental evaluation particularly challenging. Puzzle...
Visually-aware recommender systems (VRSs) enhance the semantics of user-item interactions with visual features extracted from item images when they are available. Traditionally, VRSs leverage the representational power of pretrained convolutional neural networks (CNNs) to perform the item recommendation task. The adoption of CNNs is mainly attribut...
Visual-based recommender systems (VRSs) enhance recommendation performance by integrating users' feedback with the visual features of items' images.
Recently, human-imperceptible image perturbations, defined \textit{adversarial samples}, have been shown capable of altering the VRSs performance, for example, by pushing (promoting) or nuking (demotin...
Visually-aware recommender systems (VRSs) enhance the semantics of user-item interactions with visual features extracted from item images when they are available. Traditionally, VRSs leverage the representational power of pretrained convolutional neural networks (CNNs) to perform the item recommendation task. The adoption of CNNs is mainly attribut...
Recommender Systems have shown to be an effective way to alleviate the over-choice problem and provide accurate and tailored recommendations. However, the impressive number of proposed recommendation algorithms, splitting strategies, evaluation protocols, metrics, and tasks, has made rigorous experimental evaluation particularly challenging. Puzzle...
Visually-aware recommendation leverages on visual signals of product images extracted through Deep Neural Networks to improve the recommendation performance. However, human-imperceptible adversarial noise can alter recommendation outcomes, e.g., pushing/nuking specific product categories. In this work, we provide 24 combinations of attack/defense s...
Visual-based recommender systems (VRSs) enhance recommendation performance by integrating users' feedback with the visual features of product images extracted from a deep neural network (DNN). Recently, human-imperceptible images perturbations, defined \textit{adversarial attacks}, have been demonstrated to alter the VRSs recommendation performance...
Deep learning classifiers are hugely vulnerable to adversarial examples, and their existence raised cybersecurity concerns in many tasks with an emphasis on malware detection, computer vision, and speech recognition. While there is a considerable effort to investigate attacks and defense strategies in these tasks, only limited work explores the inf...
Deep Learning-based (DL) image compression has shown prominent results compared to standard image compression techniques like JPEG, JPEG2000, BPG and WebP. Nevertheless, neither DL nor standard techniques generally can cope with critical real-world scenarios, with stringent performance constraints. In order to explore the nature of this gap, we fir...