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

Knowledge Graphs are a widely used method to represent relations betweenentities in various AI applications, and Graph Embedding has rapidly become astandard technique to represent Knowledge Graphs in such a way as to facilitateinferences and decisions. As this representation is obtained from behaviouraldata, and is not in a form readable by humans, there is a concern that it mightincorporate unintended information that could lead to biases. We proposeEXTRACT: a suite of Explainable and Transparent methods to ConTrol bias inknowledge graph embeddings, so as to assess and decrease the implicit presenceof protected information. Our method uses Canonical Correlation Analysis (CCA)to investigate the presence, extent and origins of information leaks duringtraining, then decomposes embeddings into a sum of their private attributes bysolving a linear system. Our experiments, performed on the MovieLens1M dataset,show that a range of personal attributes can be inferred from a user's viewingbehaviour and preferences, including gender, age, and occupation. Furtherexperiments, performed on the KG20C citation dataset, show that the informationabout the conference in which a paper was published can be inferred from thecitation network of that article. We propose four transparent methods tomaintain the capability of the embedding to make the intended predictionswithout retaining unwanted information. A trade-off between these two goals isobserved.

EXTRACT: Explainable Transparent Control of Bias in Embeddings