This property makes graph neural networks useful for the analysis of research dynamics, which is often conducted on time-based snapshots of bibliographic data.

We propose to use an unsupervised training objective for concept representation learning that is tailored towards bibliographic data with millions of research ...

It is suggested that concept embeddings can be solely derived from the text of associated documents without using a lookup-table embedding, ...

We propose to use an unsupervised training objective for concept representation learning that is tailored towards bibliographic data with millions of research ...

The aim of this paper is to discuss the potential and limits of deep learning for gathering insights about scientific research articles. We focus on document- ...

(2019). Inductive learning of concept representations from library-scale bibliographic corpora. In K. David, K. Geihs, M. Lange, & G. Stumme ( Eds. ), ...

Dive into the research topics of 'Inductive learning of concept representations from library-scale corpora with graph convolution'. Together they form a unique ...

Inductive learning of concept representations from library-scale bibliographic corpora. L Galke, T Melnychuk, E Seidlmayer, S Trog, K Foerstner, C Schultz ...

Inductive learning of concept representations from library-scale bibliographic corpora. In K. David, K. Geihs, M. Lange, & G. Stumme ( Eds. ), Informatik ...

Lifelong Learning of Graph Neural Networks for Open-World Node ... Inductive Learning of Concept Representations from Library-Scale Bibliographic Corpora.