Javier Sanz-Cruzado

Talks

Here, you shall find the different invited talks in seminar, workshops. While related to scientific publications, the talks shown here are not necessarily tied to one. For talks related to specific papers in conferences, please, go to the Publications page. Talks are ordered from more recent to older.

Accelerating Cross-Encoders for Biomedical Entity Linking.
AI4Biomed Group Research Meeting , University of Glasgow, Glasgow, Scotland, April 2025.
Slides

Abstract:Biomedical entity linking models disambiguate mentions in text by matching them with unique biomedical concepts. This problem is commonly addressed using a two-stage pipeline comprising an inexpensive candidate generator, which filters a subset of suitable entities for a mention, and a costly but precise reranker that provides the final matching between the mention and the concept. With the goal of applying two-stage entity linking at scale, we explore the construction of effective cross-encoder reranker models, capable of scoring multiple mention-entity pairs simultaneously. Through experiments on four entity linking datasets, we show that our cross-encoder models provide between 2.7 to 36.97 times faster training speeds and 3.8 to 26.47 times faster inference speeds than a base cross-encoder model capable of scoring only one entity, while achieving similar accuracy (differences between -3.42% to 2.76% Acc@1).

Keywords biomedicine, entity linking, cross-encoders, efficiency.
Recommending people in social networks: Algorithmic models and network diversity.
AI4Biomed Group Research Meeting , University of Glasgow, Glasgow, Scotland, October 2024.
Slides

Abstract:Contact recommendation appears as one of the most relevant problems in the confluence between recommender systems and online social networks. The goal of this problem is to identify those people in a social network with whom a user might be interested to connect. In this seminar, we explore two different aspects of contact recommendation. First, we explore the design of novel and effective algorithms, looking to increase the density of the network. For this, we adapt classical information retrieval models to recommend people in social networks and use them in three different tasks: as direct recommenders, as similarity measures in nearest neighbours schemes and as samplers and features in learning to rank. Next, we consider the potential of contact recommendation algorithms to drive the evolution of networks towards desirable properties of the network. We investigate the definition of novel metrics that quantify the effects of recommendations over the network and analyse how these changes might affect the users of the network.

Keywords social networks, recommender systems, contact recommendation, information retrieval models, diversity, novelty, redundancy, social network analysis, weak tie, evaluation, metric.
Investors are (not) always right: A comparison of transaction-based and profitability-based evaluation in financial asset recommendation.
Glasgow IR Group Seminar Series , University of Glasgow, Glasgow, Scotland, June 2024.
Slides

Abstract:Financial asset recommendation (FAR) is an emerging sub-domain of the wider recommendation field that is concerned with recommending suitable financial assets to customers, with the expectation that those customers will invest capital into a subset of those assets. FAR solutions need to learn from a combination of time-series pricing data, company fundamentals, social signals and world events, and connect the learned patterns to customer representations including their profile information (investment capacity, risk aversion) and past investments. Several strategies have been devised for the evaluation of FAR solutions, with the most prominent measuring (a) how much customers would increase their wealth if they followed their recommendations (profitability-based evaluation) and (b) the ability of the models to suggest assets on which customers will invest (transaction-based evaluation). If customers invest intelligently (and are therefore able to profit from their investments), we would expect a high correlation between both strategies. If this correlation is high, we would only need to build FAR models optimizing transaction-based evaluations. However, we cannot assume these two perspectives are necessarily correlated. Therefore, in this talk, we explore the actual relation between these two evaluation perspectives from a theoretical and empirical point of view. We also provide an in-depth analysis of the factors affecting this relationship.

Keywords recommender systems, financial recommendation, evaluation, metric, profitability, interactions.
IAA in Financial Informatics.
EPSRC Impact Acceleration Account Funding Success Sharing Session , University of Glasgow, Glasgow, Scotland, February 2024.
Slides

Abstract:As part of the Financial Informatics Theme at the University of Glasgow, between April 2023 and January 2024, we embarked in a route towards turning our research on financial recommender systems into impact. For this, we applied for funding and participated in multiple impact and innovation projects. Specifically, three EPSRC Impact Acceleration Account (IAA) projects, and an ICURe Explore project. In this talk, we present our journey towards impact and lessons that we learned in the way.

Keywords financial recommendation, research impact, research funding, impact acceleration account, ICURe Explore.
RELISON: REcommending LInks in SOcial Networks.
Glasgow IR Away Day , University of Glasgow, Glasgow, Scotland, December 2022.
Slides

Abstract:Link recommendation is an important and compelling problem at the intersection of recommender systems and online social networks. Given a user, link recommenders identify people in the platform the user might be interested in interacting with. We present RELISON, an extensible framework for running link recommendation experiments. The library provides a wide range of algorithms, along with tools for evaluating the produced recommendations. RELISON includes algorithms and metrics that consider the potential effect of recommendations on the properties of online social networks. For this reason, the library also implements network structure analysis metrics, community detection algorithms, and network diffusion simulation functionalities. The library code and documentation is available at https://github.com/ir-uam/RELISON.

Keywords social network, recommender systems, contact recommendation, social network analysis, link prediction, community detection, information diffusion.
On Transaction-Based Metrics as a Proxy for Profitability of Financial Asset Recommendations.
Glasgow IR Group Seminar Series , University of Glasgow, Glasgow, Scotland, November 2022.
Slides

Abstract:The use of recommender systems to assist in the provision of financial asset and portfolio recommendations to investors is increasing, spanning a wide range of algorithms and techniques. Several strategies have been devised for the evaluation of financial asset recommendations, with the two most prominent strategies measuring (a) the money customers could obtain if they followed the recommendations (profitability-based evaluation) and (b) the ability of models to predict future customer investments (transaction-based evaluation). If customers are effective investors, we would expect these two perspectives to be positively correlated. In this paper, we perform experiments over a new large-scale financial recommendation dataset with real customer investment transactions to validate this assumption. Surprisingly, we find that transaction and profitability-based metrics are in fact negatively correlated and moreover, algorithms that actively try to learn from past customer transactions lose money over the mid-term. A thorough analysis of model performance and customer transaction patterns over time illustrates that this is due to a set of confounding factors, namely: customers failing to beat the market with their investments; a tendency for the customers to favour different investment lengths; and the impact of global events such as the Covid-19 pandemic.

Keywords recommender systems, financial recommendation, evaluation, metric, profitability, interactions.
Recommending people in social networks: Algorithmic models and network diversity.
Glasgow IR Group Seminar Series , University of Glasgow, Glasgow, Scotland, February 2022.
Slides

Abstract:Contact recommendation appears as one of the most relevant problems in the confluence between recommender systems and online social networks. The goal of this problem is to identify those people in a social network with whom a user might be interested to connect. In this seminar, we explore two different aspects of contact recommendation. First, we explore the design of novel and effective algorithms, looking to increase the density of the network. For this, we adapt classical information retrieval models to recommend people in social networks and use them in three different tasks: as direct recommenders, as similarity measures in nearest neighbours schemes and as samplers and features in learning to rank. Next, we consider the potential of contact recommendation algorithms to drive the evolution of networks towards desirable properties of the network. We investigate the definition of novel metrics that quantify the effects of recommendations over the network and analyse how these changes might affect the users of the network.

Keywords social networks, recommender systems, contact recommendation, information retrieval models, diversity, novelty, redundancy, social network analysis, weak tie, evaluation, metric.
Contact recommendation in social networks using search methods. (In (Spanish))
HAIViS Lab Seminars , Pontificia Universidad Católica de Chile, Santiago, Chile, March 2021.
Slides

Abstract:We investigate a novel perspective to the development of effective algorithms for contact recommendation in social networks, where the problem consists of automatically predicting people that a given user may wish or benefit from connecting to in the network. Specifically, we explore the connection between contact recommendation and the text information retrieval (IR) task, by investigating the adaptation of IR models (classical and supervised) for recommending people in social networks, using only the structure of these networks. We first explore the use of adapted unsupervised IR models as direct standalone recommender systems. Seeking additional effectiveness enhancements, we further explore the use of IR models as neighbor selection methods, in place of common similarity measures, in user-based and item-based nearest-neighbors (kNN) collaborative filtering approaches. On top of this, we investigate the application of learning to rank approaches borrowed from text IR to achieve additional improvements. We report thorough experiments over data obtained from Twitter and Facebook where we observe that IR models, particularly BM25, are competitive compared to state-of-the art contact recommendation methods. We provide further empirical analysis of the additional effectiveness that can be achieved by the integration of IR models into kNN and learning to rank schemes. Our research shows that the IR models are effective in three roles: as direct contact recommenders, as neighbor selectors in collaborative filtering and as samplers and features in learning to rank.

Keywords social networks, recommender systems, contact recommendation, information retrieval models.
Contact recommendation in social networks: beyond accuracy. (In (Spanish))
NLP/IR Seminars , Universidad Española de Educación a Distancia, Madrid, Spain, July 2018.

Abstract:Contact recommendation has become a common functionality in online social platforms, and an established research topic in the social networks and recommender systems fields. Predicting and recommending links has been mainly addressed to date as an accuracy-targeting problem. In this paper we put forward a different perspective, considering that correctly predicted links may not be all equally valuable. Contact recommendation brings an opportunity to drive the structural evolution of a social network towards desirable properties of the network as a whole, beyond the sum of the isolated gains for the individual users to whom recommendations are delivered - global properties that we may want to assess and promote as explicit recommendation targets. In this perspective, we research the definition of relevant diversity metrics drawing from social network analysis concepts, and linking to prior diversity notions in recommender systems. In particular, we elaborate on the notion of weak tie recommendation as a means to enhance the structural diversity of networks. In order to show the signification of the proposed metrics, we report experiments with Twitter data illustrating how state of the art contact recommendation methods compare in terms of our metrics; we examine the tradeoff with accuracy, and we show that diverse link recommendations result in a corresponding diversity enhancement in the flow of information through the network, with potential implications in mitigating filter bubbles.

Keywords social networks, recommender systems, contact recommendation, diversity, novelty, redundancy, social network analysis, weak tie, evaluation, metric.