1,720,964 research outputs found
Human-Centered and Sustainable Recommender Systems
No full textThis tutorial explores the intersection of sustainability and recommender systems, focusing on aligning user needs and values with sustainable practices. It emphasizes two dimensions: (1) understanding and modeling users to deliver more sustainable recommendations; and (2) fostering sustainability through system design and functionality. Participants will learn how recommender systems can encourage sustainable behaviors and how to enhance system efficiency while minimizing resource consumption and ethical challenges. Through theoretical insights and hands-on sessions, this tutorial proposes discussion and actionable strategies to design human-centered, sustainable recommender systems, addressing both societal impact and technological responsibility
Training Green and Sustainable Recommendation Models: Introducing Carbon Footprint Data into Early Stopping Criteria
No full textWith the growing focus on Green AI, there is an urgent need for algorithms that are designed to minimize their environmental impact while maintaining satisfying performance. In this paper, we introduce a novel early stopping strategy that considers carbon footprint data while training a recommendation algorithm. In particular, during the training phase, our criterion epoch-by-epoch analyzes the improvement in terms of predictive accuracy and compares it to the increase in carbon emissions. Then, we analyze the trade-off between the scores, and when the accuracy improves at a rate that is not favorable, the training is stopped.
In the experimental evaluation, we showed that our strategy could significantly reduce the carbon footprint of several state-of-the-art recommendation models, with a limited decrease in accuracy and fairness. While more work is needed to automatically balance the trade-off between accuracy and emissions, this paper sheds light on the need for more sustainable recommendation models and takes a significant step toward designing green training strategies
Comparing data reduction strategies for energy-efficient green recommender systems
No full textAs recommendation algorithms become increasingly sophisticated and pervasive, their energy consumption and associated carbon emissions are rising significantly. To address this growing environmental concern, this work investigates the path toward ‘green recommender systems’ by examining how data reduction techniques can impact on algorithm performance and carbon footprint. We specifically investigated whether and how a reduction of the training data impacts the performance of several representative recommendation algorithms. To obtain a fair comparison, all the algorithms were run based on the implementations available in a popular recommendation library, i.e., RecBole, and by using the same experimental settings. Specifically, we employed distinct data reduction strategies: (a) random sampling of either users or item ratings; (b) reducing the overall dataset size; (c) filtering out more recent user ratings. Results indicate that data reduction can be a promising strategy to make recommender systems more environmentally sustainable with a relevant reduction in carbon emissions at the cost of a smaller reduction in predictive accuracy -43.38%
of emissions for LightGCN algorithm and only 3.72% loss in accuracy in a book recommendation scenario). Moreover, training recommender systems with less data makes the suggestions less prone to popularity bias. Overall, this study contributes to the ongoing challenge of developing recommendation algorithms that meet the principles of Sustainable Development Goals, by proposing the adoption of more sustainable practices in the field
Balancing carbon footprint and algorithm performance in recommender systems: A comprehensive benchmark
No full textIn this paper, we present a reproducible pipeline to benchmark the trade-off between carbon emissions and recommendation performance across 14 algorithms and three publicly available datasets. In particular, we contribute: (a) a standardized protocol to account for carbon emissions of recommendation algorithms; (b) an empirical quantification of the carbon cost of hyperparameter tuning, and (c) an evaluation of data-reduction strategies as a low-cost approach to reduce emissions while improving certain non-accuracy metrics. Unlike previous literature, which mainly focused on the trade-off between performance and emissions, our benchmark reveals the cost of hyperparameter tuning. It examines the impact of data reduction techniques on the path toward sustainability-aware recommender systems. Our results show that simpler algorithms often deliver competitive accuracy at significantly lower emissions, and that exhaustive tuning can dramatically increase carbon costs with limited accuracy gains. Generally speaking, this study aims to discuss the challenges of energy consumption in recommender systems and to develop a new generation of algorithms that prioritize sustainability. All code and experiment traces are publicly released for reproducibility on Github.
Recommender systems based on neuro-symbolic knowledge graph embeddings encoding first-order logic rules
Full text linkIn this paper, we present a knowledge-aware recommendation model based on neuro-symbolic graph embeddings that encode first-order logic rules. Our approach is based on the intuition that is the basis of neuro-symbolic AI systems: to combine deep learning and symbolic reasoning in one single model, in order to take the best out of both the paradigms. To this end, we start from a knowledge graph (KG) encoding information about users, ratings, and descriptive properties of the items and we design a model that combines background knowledge encoded in logical rules mined from the KG with explicit knowledge encoded in the triples of the KG itself to obtain a more precise representation of users and items. Specifically, our model is based on the combination of: (i) a rule learner that extracts first-order logic rules based on the information encoded in the knowledge graph; (ii) a graph embedding module, that jointly learns a vector space representation of users and items based on the triples encoded in the knowledge graph and the rules previously extracted; (iii) a recommendation module that uses the embeddings to feed a deep learning architecture that provides users with top-k recommendations. In the experimental section, we evaluate the effectiveness of our strategy on three datasets, and the results show that the combination of knowledge graph embeddings and first-order logic rules led to an improvement in the predictive accuracy and in the novelty of the recommendations. Moreover, our approach overcomes several competitive baselines, thus confirming the validity of our intuitions
RecSys CarbonAtor: Predicting Carbon Footprint of Recommendation System Models
No full textEnvironmental sustainability of AI, or Green AI, is a topic
that is getting more and more crucial in the last few years. However, AI
systems continue to improve at the cost of huge resources, neglecting the
environmental impact in terms of CO2 emissions from computations. In
this context, Recommender Systems (RS) are no exception, and the current
literature in the field pays little attention to the concept of Green AI.
In this paper, we propose a tool that aims at estimating the CO2 emitted
by a recommendation model. Our contributions are twofold: first, we
built a regression dataset that can be used to feed a regression model aiming
at estimating the emissions or RS models; this dataset can be easily
expanded, so it can be considered a relevant resource for the whole community.
Second, we compared several state-of-the-art regression models
to assess which performs the best and in which settings. Results show
that Random Forest is the best performing model to effectively estimate
the CO2 emissions produced by recommendation model
Evaluating Content-based Pre-Training Strategies for a Knowledge-aware Recommender System based on Graph Neural Networks
No full textIn this paper, we introduce a Knowledge-aware Recommender System (KARS) based on Graph Neural Networks that exploit pre-trained content-based embeddings to improve the representation of users and items. Our approach relies on the intuition that textual features can describe the items in the catalog from a different point of view, so they are worth to be exploited to provide users with more accurate recommendations. Accordingly, we used encoding techniques to learn a pre-trained representation of the items in the catalogue based on textual content, and we used these embeddings to feed the input layer of a KARS based on GCNs. In this way, the GCN is able to encode both the knowledge coming from the unstructured content and the structured knowledge provided by the KG (ratings and item descriptive properties). As shown in our experiments, the exploitation of pre-trained embeddings improves the predictive accuracy of the KARS, which overcomes all the baselines we considered in several experimental settings
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
