Friendly neighbors: Contextualized sequence-to-sequence link prediction

A Kochsiek, A Saxena, I Nair, R Gemulla - arXiv preprint arXiv:2305.13059, 2023 - arxiv.org
We propose KGT5-context, a simple sequence-to-sequence model for link prediction (LP) in
knowledge graphs (KG). Our work expands on KGT5, a recent LP model that exploits textual …

Deep learning-based immunohistochemical estimation of breast cancer via ultrasound image applications

D Yan, Z Zhao, J Duan, J Qu, L Shi, Q Wang… - Frontiers in …, 2024 - frontiersin.org
Background Breast cancer is the key global menace to women's health, which ranks first by
mortality rate. The rate reduction and early diagnostics of breast cancer are the mainstream …

The Role of Graph Topology in the Performance of Biomedical Knowledge Graph Completion Models

A Cattaneo, S Bonner, T Martynec, C Luschi… - arXiv preprint arXiv …, 2024 - arxiv.org
Knowledge Graph Completion has been increasingly adopted as a useful method for
several tasks in biomedical research, like drug repurposing or drug-target identification. To …

HUNIPU: Efficient Hungarian Algorithm on IPUs

C Huang, AM Graphcore, JD Graphcore… - 2024 IEEE 40th …, 2024 - ieeexplore.ieee.org
The Hungarian algorithm is a fundamental approach for a number of matching problems that
find corresponding elements in two sets. For instance, the optimal alignment of proteins. Due …

Towards Linking Graph Topology to Model Performance for Biomedical Knowledge Graph Completion

A Cattaneo, T Martynec, S Bonner, C Luschi… - ICML'24 Workshop ML … - openreview.net
Knowledge Graph Completion has been increasingly adopted as a useful method for
several tasks in biomedical research, like drug repurposing or drug-target identification. To …