paula gomez duran - Academia.edu (original) (raw)

Uploads

Papers by paula gomez duran

Research paper thumbnail of Graph Convolutional Embeddings for Recommender Systems

arXiv (Cornell University), Mar 5, 2021

Modern recommender systems (RS) work by processing a number of signals that can be inferred from ... more Modern recommender systems (RS) work by processing a number of signals that can be inferred from large sets of user-item interaction data. The main signal to analyze stems from the raw matrix that represents interactions. However, we can increase the performance of RS by considering other kinds of signals like the context of interactions, which could be, for example, the time or date of the interaction, the user location, or sequential data corresponding to the historical interactions of the user with the system. These complex, context-based interaction signals are characterized by a rich relational structure that can be represented by a multi-partite graph. Graph Convolutional Networks (GCNs) have been used successfully in collaborative filtering with simple user-item interaction data. In this work, we generalize the use of GCNs for N-partide graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures. More specifically, we define a graph convolutional embedding layer for N-partide graphs that processes user-item-context interactions, and constructs node embeddings by leveraging their relational structure. Experiments on several datasets from recommender systems to drug re-purposing show the benefits of the introduced GCN embedding layer by measuring the performance of different context-enriched tasks. CCS CONCEPTS • Information systems → Recommender systems.

Research paper thumbnail of Contextual TV Show Recommendation

Frontiers in artificial intelligence and applications, Oct 17, 2022

Recommender systems are a form of artificial intelligence that is used to suggest items to users ... more Recommender systems are a form of artificial intelligence that is used to suggest items to users of digital platforms. They use large data sets to infer models of users' behavior and preferences in order to recommend items that the user may be interested in. Following the trend imposed by digital media companies and willing to adapt to the media consumption habits of their customers, TV broadcasters are starting to realize the potential of recommender systems to personalize the access to their online catalog. By understanding what viewers are watching and what they might like, TV broadcasters can improve the quality of their programming, increase viewership, and attract new viewers. In this work, we analyze one specific group of users that TV broadcasters must take into account when creating a recommender system: non-logged users. In this scenario the challenge is to use contextual information about the interaction in order to predict recommendations, as it is not feasible to use any kind of information about the user. We propose a method to leverage data from other type of users (logged users and identified devices) by using Graph Convolutional Networks in order to come up with a more accurate recommender system for unidentified users.

Research paper thumbnail of A web-based user interface for browsing and annotating image collections using a state-of-the-art content-based image search engine

This thesis consists of developing a web user interface for a content-based image retrieval (CBIR... more This thesis consists of developing a web user interface for a content-based image retrieval (CBIR) system in order to provide a visualization of the obtained results and eventually to improve them by capturing the user's feedback.

Research paper thumbnail of Graph Convolutional Embeddings for Recommender Systems

IEEE Access, 2021

Modern recommender systems (RS) work by processing a number of signals that can be inferred from ... more Modern recommender systems (RS) work by processing a number of signals that can be inferred from large sets of user-item interaction data. The main signal to analyze stems from the raw matrix that represents interactions. However, we can increase the performance of RS by considering other kinds of signals like the context of interactions, which could be, for example, the time or date of the interaction, the user location, or sequential data corresponding to the historical interactions of the user with the system. These complex, context-based interaction signals are characterized by a rich relational structure that can be represented by a multi-partite graph. Graph Convolutional Networks (GCNs) have been used successfully in collaborative filtering with simple user-item interaction data. In this work, we generalize the use of GCNs for N-partite graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures. More specifically, we define a graph convolutional embedding layer for N-partite graphs that processes user-item-context interactions and constructs node embeddings by leveraging their relational structure. Experiments on several datasets show the benefits of the introduced GCN embedding layer by measuring the performance of different context-enriched tasks.

Research paper thumbnail of Demonstration of an Open Source Framework for Qualitative Evaluation of CBIR Systems

Proceedings of the 26th ACM international conference on Multimedia, 2018

Evaluating image retrieval systems in a quantitative way, for example by computing measures like ... more Evaluating image retrieval systems in a quantitative way, for example by computing measures like mean average precision, allows for objective comparisons with a ground-truth. However, in cases where ground-truth is not available, the only alternative is to collect feedback from a user. us, qualitative assessments become important to be er understand how the system works. Visualizing the results could be, in some scenarios, the only way to evaluate the results obtained and also the only opportunity to identify that a system is failing. is necessitates developing a User Interface (UI) for a Content Based Image Retrieval (CBIR) system that allows visualization of results and improvement via capturing user relevance feedback. A well-designed UI facilitates understanding of the performance of the system, both in cases where it works well and perhaps more importantly those which highlight the need for improvement. Our open-source system implements three components to facilitate researchers to quickly develop these capabilities for their retrieval engine. We present: a web-based user interface to visualize retrieval results and collect user annotations; a server that simpli es connection with any underlying CBIR system; and a server that manages the search engine data. e so ware itself is described in a separate submission to the ACM MM Open Source So ware Competition.

Research paper thumbnail of Graph Convolutional Embeddings for Recommender Systems

arXiv (Cornell University), Mar 5, 2021

Modern recommender systems (RS) work by processing a number of signals that can be inferred from ... more Modern recommender systems (RS) work by processing a number of signals that can be inferred from large sets of user-item interaction data. The main signal to analyze stems from the raw matrix that represents interactions. However, we can increase the performance of RS by considering other kinds of signals like the context of interactions, which could be, for example, the time or date of the interaction, the user location, or sequential data corresponding to the historical interactions of the user with the system. These complex, context-based interaction signals are characterized by a rich relational structure that can be represented by a multi-partite graph. Graph Convolutional Networks (GCNs) have been used successfully in collaborative filtering with simple user-item interaction data. In this work, we generalize the use of GCNs for N-partide graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures. More specifically, we define a graph convolutional embedding layer for N-partide graphs that processes user-item-context interactions, and constructs node embeddings by leveraging their relational structure. Experiments on several datasets from recommender systems to drug re-purposing show the benefits of the introduced GCN embedding layer by measuring the performance of different context-enriched tasks. CCS CONCEPTS • Information systems → Recommender systems.

Research paper thumbnail of Contextual TV Show Recommendation

Frontiers in artificial intelligence and applications, Oct 17, 2022

Recommender systems are a form of artificial intelligence that is used to suggest items to users ... more Recommender systems are a form of artificial intelligence that is used to suggest items to users of digital platforms. They use large data sets to infer models of users' behavior and preferences in order to recommend items that the user may be interested in. Following the trend imposed by digital media companies and willing to adapt to the media consumption habits of their customers, TV broadcasters are starting to realize the potential of recommender systems to personalize the access to their online catalog. By understanding what viewers are watching and what they might like, TV broadcasters can improve the quality of their programming, increase viewership, and attract new viewers. In this work, we analyze one specific group of users that TV broadcasters must take into account when creating a recommender system: non-logged users. In this scenario the challenge is to use contextual information about the interaction in order to predict recommendations, as it is not feasible to use any kind of information about the user. We propose a method to leverage data from other type of users (logged users and identified devices) by using Graph Convolutional Networks in order to come up with a more accurate recommender system for unidentified users.

Research paper thumbnail of A web-based user interface for browsing and annotating image collections using a state-of-the-art content-based image search engine

This thesis consists of developing a web user interface for a content-based image retrieval (CBIR... more This thesis consists of developing a web user interface for a content-based image retrieval (CBIR) system in order to provide a visualization of the obtained results and eventually to improve them by capturing the user's feedback.

Research paper thumbnail of Graph Convolutional Embeddings for Recommender Systems

IEEE Access, 2021

Modern recommender systems (RS) work by processing a number of signals that can be inferred from ... more Modern recommender systems (RS) work by processing a number of signals that can be inferred from large sets of user-item interaction data. The main signal to analyze stems from the raw matrix that represents interactions. However, we can increase the performance of RS by considering other kinds of signals like the context of interactions, which could be, for example, the time or date of the interaction, the user location, or sequential data corresponding to the historical interactions of the user with the system. These complex, context-based interaction signals are characterized by a rich relational structure that can be represented by a multi-partite graph. Graph Convolutional Networks (GCNs) have been used successfully in collaborative filtering with simple user-item interaction data. In this work, we generalize the use of GCNs for N-partite graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures. More specifically, we define a graph convolutional embedding layer for N-partite graphs that processes user-item-context interactions and constructs node embeddings by leveraging their relational structure. Experiments on several datasets show the benefits of the introduced GCN embedding layer by measuring the performance of different context-enriched tasks.

Research paper thumbnail of Demonstration of an Open Source Framework for Qualitative Evaluation of CBIR Systems

Proceedings of the 26th ACM international conference on Multimedia, 2018

Evaluating image retrieval systems in a quantitative way, for example by computing measures like ... more Evaluating image retrieval systems in a quantitative way, for example by computing measures like mean average precision, allows for objective comparisons with a ground-truth. However, in cases where ground-truth is not available, the only alternative is to collect feedback from a user. us, qualitative assessments become important to be er understand how the system works. Visualizing the results could be, in some scenarios, the only way to evaluate the results obtained and also the only opportunity to identify that a system is failing. is necessitates developing a User Interface (UI) for a Content Based Image Retrieval (CBIR) system that allows visualization of results and improvement via capturing user relevance feedback. A well-designed UI facilitates understanding of the performance of the system, both in cases where it works well and perhaps more importantly those which highlight the need for improvement. Our open-source system implements three components to facilitate researchers to quickly develop these capabilities for their retrieval engine. We present: a web-based user interface to visualize retrieval results and collect user annotations; a server that simpli es connection with any underlying CBIR system; and a server that manages the search engine data. e so ware itself is described in a separate submission to the ACM MM Open Source So ware Competition.