Stefano Cereda

Stefano Cereda

Auto-generated profile, based on publicly available information

Stefano Cereda

Politecnico di Milano, Milano, Italy

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
26 February 2019 in User Modeling and User-Adapted Interaction
Verified
Journal Article
Open access
PDF file
YDYashar Deldjoo
Yashar Deldjoo
MDMaurizio Ferrari Dacrema
Maurizio Ferrari Dacrema
MCMihai Gabriel Constantin
Mihai Gabriel Constantin
HEHamid Eghbal-zadeh
Hamid Eghbal-zadeh
SCStefano Cereda
Stefano Cereda
PCPaolo Cremonesi
Paolo Cremonesi
As of today, most movie recommendation services base their recommendations on collaborative filtering (CF) and/or content-based filtering (CBF) models that use metadata (e.g., genre or cast). In most video-on-demand and streaming services, however, new movies and TV series are continuously added. CF models are unable to make predictions in such a scenario, since the newly added videos lack interactions—a problem technically known as new item cold start (CS). Currently, the most common approach to this problem is to switch to a purely CBF method, usually by exploiting textual metadata. This approach is known to have lower accuracy than CF because it ignores useful collaborative information and relies on human-generated textual metadata, which are expensive to collect and often prone to errors. User-generated content, such as tags, can also be rare or absent in CS situations. In this paper, we introduce a new movie recommender system that addresses the new item problem in the movie domain by (i) integrating state-of-the-art audio and visual descriptors, which can be automatically extracted from video content and constitute what we call the movie genome; (ii) exploiting an effective data fusion method named canonical correlation analysis, which was successfully tested in our previous works Deldjoo et al. (in: International Conference on Electronic Commerce and Web Technologies. Springer, Berlin, pp 34–45, 2016b ; Proceedings of the Twelfth ACM Conference on Recommender Systems. ACM, 2018b ), to better exploit complementary information between different modalities; (iii) proposing a two-step hybrid approach which trains a CF model on warm items (items with interactions) and leverages the learned model on the movie genome to recommend cold items (items without interactions). Experimental validation is carried out using a system-centric study on a large-scale, real-world movie recommendation dataset both in an absolute cold start and in a cold to warm transition; and a user-centric online experiment measuring different subjective aspects, such as satisfaction and diversity. Results show the benefits of this approach compared to existing approaches.

27 August 2017
Verified
Conference Paper
Open access
MEMehdi Elahi
Mehdi Elahi
YDYashar Deldjoo
Yashar Deldjoo
FMFarshad Bakhshandegan Moghaddam
Farshad Bakhshandegan Moghaddam
LCLeonardo Cella
Leonardo Cella
SCStefano Cereda
Stefano Cereda
PCPaolo Cremonesi
Paolo Cremonesi
In the last years, there has been much attention given to the semantic gap problem in multimedia retrieval systems. Much effort has been devoted to bridge this gap by building tools for the extraction of high-level, semantics-based features from multimedia content, as low-level features are not considered useful because they deal primarily with representing the perceived content rather than the semantics of it. In this paper, we explore a different point of view by leveraging the gap between low-level and high-level features. We experiment with a recent approach for movie recommendation that extract low-level Mise-en-Scéne features from multimedia content and combine it with high-level features provided by the wisdom of the crowd. To this end, we first performed an offline performance assessment by implementing a pure content-based recommender system with three different versions of the same algorithm, respectively based on (i) conventional movie attributes, (ii) mise-en-scene features, and (iii) a hybrid method that interleaves recommendations based on movie attributes and mise-en-scene features. In a second study, we designed an empirical study involving 100 subjects and collected data regarding the quality perceived by the users. Results from both studies show that the introduction of mise-en-scéne features in conjunction with traditional movie attributes improves both offline and online quality of recommendations.

16 June 2020
Verified
Conference Paper
Open access
SCStefano Cereda
Stefano Cereda
GPGianluca Palermo
Gianluca Palermo
PCPaolo Cremonesi
Paolo Cremonesi
SDStefano Doni
Stefano Doni
Selecting the right compiler optimisations has a severe impact on programs' performance. Still, the available optimisations keep increasing, and their effect depends on the specific program, making the task human intractable. Researchers proposed several techniques to search in the space of compiler optimisations. Some approaches focus on finding better search algorithms, while others try to speed up the search by leveraging previously collected knowledge. The possibility to effectively reuse previous compilation results inspired us toward the investigation of techniques derived from the Recommender Systems field. The proposed approach exploits previously collected knowledge and improves its characterisation over time. Differently from current state-of-the-art solutions, our approach is not based on performance counters but relies on Reaction Matching, an algorithm able to characterise programs looking at how they react to different optimisation sets. The proposed approach has been validated using two widely used benchmark suites, cBench and PolyBench, including 54 different programs. Our solution, on average, extracted 90% of the available performance improvement 10 iterations before current state-of-the-art solutions,which corresponds to 40% fewer compilations and performance tests to perform.

9 July 2017
Verified
Conference Paper
Open access
PDF file
LCLeonardo Cella
Leonardo Cella
SCStefano Cereda
Stefano Cereda
MQMassimo Quadrana
Massimo Quadrana
PCPaolo Cremonesi
Paolo Cremonesi
Item-based recommender systems suggest products based on the similarities between items computed either from past user preferences (collaborative filtering) or from item content features (content-based filtering). Collaborative filtering has been proven to outperform content-based filtering in a variety of scenarios. However, in item cold-start, collaborative filtering cannot be used directly since past user interactions are not available for the newly added items. Hence, content-based filtering is usually the only viable option left.