Learning multi-resolution representations of research patterns in bibliographic networks

Lee, O-Joun; Jeon, Hyeon-Ju; Jung, Jason J.

doi:10.1016/j.joi.2020.101126

Cited by 9 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our study proposes a novel approach using Graph Neural Networks (GNNs) [7,8,9] to estimate the impact of observations independently of the system's structure. GNNs have been increasingly employed in meteorological predictions, including solar radiation and sea surface temperature predictions, by capturing variable interactions in neighboring regions [10,11,12].…”

Section: Introductionmentioning

confidence: 99%

JEON, Beomseok (BJ): Seoul/Republic of Korea

Jeon

2019

Leadership in Movement Disorders

View full text Add to dashboard Cite

This paper investigates the impact of observations on atmospheric state estimation in weather forecasting systems using graph neural networks (GNNs) and explainability methods. We integrate observation and Numerical Weather Prediction (NWP) points into a meteorological graph, extracting k-hop subgraphs centered on NWP points. Self-supervised GNNs are employed to estimate the atmospheric state by aggregating data within these k-hop radii. The study applies gradient-based explainability methods to quantify the significance of different observations in the estimation process. Evaluated with data from 11 satellite and land-based observations, the results highlight the effectiveness of visualizing the importance of observation types, enhancing the understanding and optimization of observational data in weather forecasting.

show abstract

Section: Introductionmentioning

confidence: 99%

JEON, Beomseok (BJ): Seoul/Republic of Korea

Jeon

2019

Leadership in Movement Disorders

View full text Add to dashboard Cite

show abstract

“…The literature already presents some works that sustain this claim, proposing different approaches to use it, in particular it was firstly conceptualized by the first author of this paper in [ 64 ]. Furthermore, it was used in [ 65 ] and in Specter [ 22 ] that uses direct citation to create a positive tuple. The foundation of this idea is that two given papers, where at least one cites the other, have hidden semantic relationships; they could be about the same arguments, have a joint related work, or other similarities.…”

Section: Methodsmentioning

confidence: 99%

Efficient Self-Supervised Metric Information Retrieval: A Bibliography Based Method Applied to COVID Literature

Moro

Valgimigli

2021

Sensors

View full text Add to dashboard Cite

The literature on coronaviruses counts more than 300,000 publications. Finding relevant papers concerning arbitrary queries is essential to discovery helpful knowledge. Current best information retrieval (IR) use deep learning approaches and need supervised train sets with labeled data, namely to know a priori the queries and their corresponding relevant papers. Creating such labeled datasets is time-expensive and requires prominent experts’ efforts, resources insufficiently available under a pandemic time pressure. We present a new self-supervised solution, called SUBLIMER, that does not require labels to learn to search on corpora of scientific papers for most relevant against arbitrary queries. SUBLIMER is a novel efficient IR engine trained on the unsupervised COVID-19 Open Research Dataset (CORD19), using deep metric learning. The core point of our self-supervised approach is that it uses no labels, but exploits the bibliography citations from papers to create a latent space where their spatial proximity is a metric of semantic similarity; for this reason, it can also be applied to other domains of papers corpora. SUBLIMER, despite is self-supervised, outperforms the Precision@5 (P@5) and Bpref of the state-of-the-art competitors on CORD19, which, differently from our approach, require both labeled datasets and a number of trainable parameters that is an order of magnitude higher than our.

show abstract

“…Several studies have been proposed to capture the global structure information (Lee, Jeon, and Jung 2021). WRGAT aims to break the limitations of GNNs by using multirelations between distant nodes in graphs (Suresh et al 2021).…”

Section: Related Workmentioning

confidence: 99%

Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-Based Similarity

Hoang,

Lee

2024

AAAI

View full text Add to dashboard Cite

Graph representation learning (GRL) methods, such as graph neural networks and graph transformer models, have been successfully used to analyze graph-structured data, mainly focusing on node classification and link prediction tasks. However, the existing studies mostly only consider local connectivity while ignoring long-range connectivity and the roles of nodes. In this paper, we propose Unified Graph Transformer Networks (UGT) that effectively integrate local and global structural information into fixed-length vector representations. First, UGT learns local structure by identifying the local sub-structures and aggregating features of the k-hop neighborhoods of each node. Second, we construct virtual edges, bridging distant nodes with structural similarity to capture the long-range dependencies. Third, UGT learns unified representations through self-attention, encoding structural distance and p-step transition probability between node pairs. Furthermore, we propose a self-supervised learning task that effectively learns transition probability to fuse local and global structural features, which could then be transferred to other downstream tasks. Experimental results on real-world benchmark datasets over various downstream tasks showed that UGT significantly outperformed baselines that consist of state-of-the-art models. In addition, UGT reaches the third-order Weisfeiler-Lehman power to distinguish non-isomorphic graph pairs.

show abstract

Learning multi-resolution representations of research patterns in bibliographic networks

Cited by 9 publications

References 36 publications

JEON, Beomseok (BJ): Seoul/Republic of Korea

JEON, Beomseok (BJ): Seoul/Republic of Korea

Efficient Self-Supervised Metric Information Retrieval: A Bibliography Based Method Applied to COVID Literature

Transitivity-Preserving Graph Representation Learning for Bridging Local Connectivity and Role-Based Similarity

Contact Info

Product

Resources

About