Jeffrey Sardina
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jeffrey Sardina has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Declan O’ Sullivan
Trinity College Dublin
4 shared publications - John D. Kelleher
Trinity College Dublin
4 shared publications - Alok Debnath
ADAPT Centre, School of Computer Science and Statistics, Trinity College Dublin, Ireland
1 shared publication - Callie Sardina
Boston College
1 shared publication
Latest Publications
- 15 December 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Semantic Computing
- Vol. 19 (04) , 659-681
Structural Alignment of Knowledge Graphs and Link Prediction: A Survey of the Literature
Knowledge Graphs (KGs) have seen ever-increasing use in a breadth of academic and applied settings. In tandem with the increasing use of KGs, there has been an increased interest in the Link Prediction (LP) task, which aims to predict new information about the domain of a KG based on the data in the KG. While Knowledge Graph Embedding Models (KGEMs) have predominantly been used to solve the LP task in the state-of-the-art, both KGEMs and the LP task remain incompletely characterized in terms of how they relate to the structure of the KG being learned. This is of particular concern in light of recent studies showing that KG structure can be both a significant source of bias in LP learning and at least partially determinant of LP performance. This paper seeks to address this gap in the state-of-the-art by providing a survey of the established relationships between LP, KGEMs, and KG structure in the literature. This work then proposes the Structural Alignment Hypothesis as a unifying perspective for modeling the data-task relationship between KGs and LP. It is the hope of the authors that this work will contribute to a more holistic understanding of KGs, KGEMs, and the LP task.
- 15 December 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Semantic Computing
- Vol. 19 (04) , 659-681
Structural Alignment of Knowledge Graphs and Link Prediction: A Survey of the Literature
Knowledge Graphs (KGs) have seen ever-increasing use in a breadth of academic and applied settings. In tandem with the increasing use of KGs, there has been an increased interest in the Link Prediction (LP) task, which aims to predict new information about the domain of a KG based on the data in the KG. While Knowledge Graph Embedding Models (KGEMs) have predominantly been used to solve the LP task in the state-of-the-art, both KGEMs and the LP task remain incompletely characterized in terms of how they relate to the structure of the KG being learned. This is of particular concern in light of recent studies showing that KG structure can be both a significant source of bias in LP learning and at least partially determinant of LP performance. This paper seeks to address this gap in the state-of-the-art by providing a survey of the established relationships between LP, KGEMs, and KG structure in the literature. This work then proposes the Structural Alignment Hypothesis as a unifying perspective for modeling the data-task relationship between KGs and LP. It is the hope of the authors that this work will contribute to a more holistic understanding of KGs, KGEMs, and the LP task.
- 3 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11-19
A Survey on Knowledge Graph Structure and Knowledge Graph Embeddings
Knowledge Graphs (KGs) and their machine learning counterpart, Knowledge Graph Embedding Models (KGEMs), have seen ever-increasing use in a wide variety of academic and applied settings. In particular, KGEMs are typically applied to KGs to solve the link prediction task; i.e. to predict new facts in the domain of a KG based on existing, observed facts. While this approach has been shown substantial power in many end-use cases, it remains incompletely characterised in terms of how KGEMs react differently to KG structure. This is of particular concern in light of recent studies showing that KG structure can be a significant source of bias as well as partially determinant of overall KGEM performance. This paper seeks to address this gap in the state-of-the-art. This paper provides, to the authors' knowledge, the first comprehensive survey exploring established relationships of Knowledge Graph Embedding Models and Graph structure in the literature. It is the hope of the authors that this work will inspire further studies in this area, and contribute to a more holistic understanding of KGs, KGEMs, and the link prediction task.
- 3 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 11-19
A Survey on Knowledge Graph Structure and Knowledge Graph Embeddings
Knowledge Graphs (KGs) and their machine learning counterpart, Knowledge Graph Embedding Models (KGEMs), have seen ever-increasing use in a wide variety of academic and applied settings. In particular, KGEMs are typically applied to KGs to solve the link prediction task; i.e. to predict new facts in the domain of a KG based on existing, observed facts. While this approach has been shown substantial power in many end-use cases, it remains incompletely characterised in terms of how KGEMs react differently to KG structure. This is of particular concern in light of recent studies showing that KG structure can be a significant source of bias as well as partially determinant of overall KGEM performance. This paper seeks to address this gap in the state-of-the-art. This paper provides, to the authors' knowledge, the first comprehensive survey exploring established relationships of Knowledge Graph Embedding Models and Graph structure in the literature. It is the hope of the authors that this work will inspire further studies in this area, and contribute to a more holistic understanding of KGs, KGEMs, and the link prediction task.
- Open Access
- 11 September 2024
- Published by IOS Press
- p. 106-122
TWIG-I: Embedding-Free Link Prediction and Cross-KG Transfer Learning Using a Small Neural Architecture
Knowledge Graphs (KGs) are relational knowledge bases that represent facts as a set of labelled nodes and the labelled relations between them. Their machine learning counterpart, Knowledge Graph Embeddings (KGEs), learn to predict new facts based on the data contained in a KG – the so-called link prediction task. To date, almost all forms of link prediction for KGs rely on some form of embedding model, and KGEs hold state-of-the-art status for link prediction. In this paper, we present TWIG-I (Topologically-Weighted Intelligence Generation for Inference), a novel link prediction system that can represent the features of a KG in latent space without using node or edge embeddings. TWIG-I shows mixed performance relative to state-of-the-art KGE models – at times exceeding or falling short of baseline performance. However, unlike KGEs, TWIG-I can be natively used for transfer learning across distinct KGs. We show that using transfer learning with TWIG-I can lead to increases in performance in some cases both over KGE baselines and over TWIG-I models trained without finetuning. While these results are still mixed, TWIG-I clearly demonstrates that structural features are sufficient to solve the link prediction task in the absence of embeddings. Finally, TWIG-I opens up cross-KG transfer learning as a new direction in link prediction research and application.
- 11 September 2024
- Published by IOS Press
- p. 106-122
Open AccessTWIG-I: Embedding-Free Link Prediction and Cross-KG Transfer Learning Using a Small Neural Architecture
Knowledge Graphs (KGs) are relational knowledge bases that represent facts as a set of labelled nodes and the labelled relations between them. Their machine learning counterpart, Knowledge Graph Embeddings (KGEs), learn to predict new facts based on the data contained in a KG – the so-called link prediction task. To date, almost all forms of link prediction for KGs rely on some form of embedding model, and KGEs hold state-of-the-art status for link prediction. In this paper, we present TWIG-I (Topologically-Weighted Intelligence Generation for Inference), a novel link prediction system that can represent the features of a KG in latent space without using node or edge embeddings. TWIG-I shows mixed performance relative to state-of-the-art KGE models – at times exceeding or falling short of baseline performance. However, unlike KGEs, TWIG-I can be natively used for transfer learning across distinct KGs. We show that using transfer learning with TWIG-I can lead to increases in performance in some cases both over KGE baselines and over TWIG-I models trained without finetuning. While these results are still mixed, TWIG-I clearly demonstrates that structural features are sufficient to solve the link prediction task in the absence of embeddings. Finally, TWIG-I opens up cross-KG transfer learning as a new direction in link prediction research and application.
- Open Access
- 23 February 2023
- Published by Springer Nature
- p. 68-80
Analysis of Attention Mechanisms in Box-Embedding Systems
Large-scale Knowledge Graphs (KGs) have recently gained considerable research attention for their ability to model the inter- and intra- relationships of data. However, the huge scale of KGs has necessitated the use of querying methods to facilitate human use. Question Answering (QA) systems have shown much promise in breaking down this human-machine barrier. A recent QA model that achieved state-of-the-art performance, Query2box, modelled queries on a KG using box embeddings with an attention mechanism backend to compute the intersections of boxes for query resolution. In this paper, we introduce a new model, Query2Geom, which replaces the Query2box attention mechanism with a novel, exact geometric calculation. Our findings show that Query2Geom generally matches the performance of Query2box while having many fewer parameters. Our analysis of the two models leads us to formally describe the interaction between knowledge graph data and box embeddings with the concepts of semantic-geometric alignment and mismatch. We create the Attention Deviation Metric as a measure of how well the geometry of box embeddings captures the semantics of a knowledge graph, and apply it to explain the difference in performance between Query2box and Query2Geom. We conclude that Query2box’s attention mechanism operates using “latent intersections” that attend to the semantic properties in embeddings not expressed in box geometry, acting as a limit on model interpretability. Finally, we generalise our results and propose that semantic-geometric mismatch is a more general property of attention mechanisms, and provide future directions on how to formally model the interaction between attention and latent semantics.
- 23 February 2023
- Published by Springer Nature
- p. 68-80
Open AccessAnalysis of Attention Mechanisms in Box-Embedding Systems
Large-scale Knowledge Graphs (KGs) have recently gained considerable research attention for their ability to model the inter- and intra- relationships of data. However, the huge scale of KGs has necessitated the use of querying methods to facilitate human use. Question Answering (QA) systems have shown much promise in breaking down this human-machine barrier. A recent QA model that achieved state-of-the-art performance, Query2box, modelled queries on a KG using box embeddings with an attention mechanism backend to compute the intersections of boxes for query resolution. In this paper, we introduce a new model, Query2Geom, which replaces the Query2box attention mechanism with a novel, exact geometric calculation. Our findings show that Query2Geom generally matches the performance of Query2box while having many fewer parameters. Our analysis of the two models leads us to formally describe the interaction between knowledge graph data and box embeddings with the concepts of semantic-geometric alignment and mismatch. We create the Attention Deviation Metric as a measure of how well the geometry of box embeddings captures the semantics of a knowledge graph, and apply it to explain the difference in performance between Query2box and Query2Geom. We conclude that Query2box’s attention mechanism operates using “latent intersections” that attend to the semantic properties in embeddings not expressed in box geometry, acting as a limit on model interpretability. Finally, we generalise our results and propose that semantic-geometric mismatch is a more general property of attention mechanisms, and provide future directions on how to formally model the interaction between attention and latent semantics.