English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Scoring functions (SFs), which measure the plausibility of triplets inknowledge graph (KG), have become the crux of KG embedding. Lots of SFs, whichtarget at capturing different kinds of relations in KGs, have been designed byhumans in recent years. However, as relations can exhibit complex patterns thatare hard to infer before training, none of them can consistently perform betterthan others on existing benchmark data sets. In this paper, inspired by therecent success of automated machine learning (AutoML), we propose toautomatically design SFs (AutoSF) for distinct KGs by the AutoML techniques.However, it is non-trivial to explore domain-specific information here to makeAutoSF efficient and effective. We firstly identify a unified representationover popularly used SFs, which helps to set up a search space for AutoSF. Then,we propose a greedy algorithm to search in such a space efficiently. Thealgorithm is further sped up by a filter and a predictor, which can avoidrepeatedly training SFs with same expressive ability and help removing badcandidates during the search before model training. Finally, we performextensive experiments on benchmark data sets. Results on link prediction andtriplets classification show that the searched SFs by AutoSF, are KG dependent,new to the literature, and outperform the state-of-the-art SFs designed byhumans.

AutoSF: Searching Scoring Functions for Knowledge Graph Embedding