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

The construction of large open knowledge bases (OKBs) is integral to manyapplications in the field of mobile computing. Noun phrases and relationalphrases in OKBs often suffer from redundancy and ambiguity, which calls for theinvestigation on OKB canonicalization. However, in order to meet therequirements of some privacy protection regulations and to ensure thetimeliness of the data, the canonicalized OKB often needs to remove somesensitive information or outdated data. The machine unlearning in OKBcanonicalization is an excellent solution to the above problem. Currentsolutions address OKB canonicalization by devising advanced clusteringalgorithms and using knowledge graph embedding (KGE) to further facilitate thecanonicalization process. Effective schemes are urgently needed to fullysynergise machine unlearning with clustering and KGE learning. To this end, weput forward a multi-task unlearning framework, namely MulCanon, to tacklemachine unlearning problem in OKB canonicalization. Specifically, the noisecharacteristics in the diffusion model are utilized to achieve the effect ofmachine unlearning for data in OKB. MulCanon unifies the learning objectives ofdiffusion model, KGE and clustering algorithms, and adopts a two-stepmulti-task learning paradigm for training. A thorough experimental study onpopular OKB canonicalization datasets validates that MulCanon achieves advancedmachine unlearning effects.

Open Knowledge Base Canonicalization with Multi-task Unlearning