Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319586100> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4319586100 abstract "With graph-structured tremendous information, Knowledge Graphs (KG) aroused increasing interest in aca-demic research and industrial applications. Recent studies have shown demographic bias, in terms of sensitive attributes (e.g., gender and race), exist in the learned representations of KG entities. Such bias negatively affects specific popu-lations, especially minorities and underrepresented groups, and exacerbates machine learning-based human inequality. Adversariallearning is regarded as an effective way to alleviate bias in the representation learning model by simultaneously training a task-specific predictor and a sensitive attribute-specific discriminator. However, due to the unique challenge caused by topological structure and the comprehensive re-lationship between knowledge entities, adversarial learning-based debiasing is rarely studied in representation learning in knowledge graphs. In this paper, we propose a framework to learn unbiased representations for nodes and edges in knowledge graph mining. Specifically, we integrate a simple-but-effective normalization technique with Graph Neural Networks (GNNs) to constrain the weights updating process. Moreover, as a work-in-progress paper, we also find that the introduced weights normalization technique can mitigate the pitfalls of instability in adversarial debasing towards fair-and-stable machine learning. We evaluate the proposed framework on a benchmarking graph with multiple edge types and node types. The experimental results show that our model achieves comparable or better gender fairness over three competitive baselines on Equality of Odds. Importantly, our superiority in the fair model does not scarify the performance in the knowledge graph task (i.e., multi-class edge classification)." @default.
- W4319586100 created "2023-02-09" @default.
- W4319586100 creator A5031804038 @default.
- W4319586100 creator A5038076471 @default.
- W4319586100 creator A5090913655 @default.
- W4319586100 date "2022-11-01" @default.
- W4319586100 modified "2023-09-27" @default.
- W4319586100 title "Towards Fair Representation Learning in Knowledge Graph with Stable Adversarial Debiasing" @default.
- W4319586100 cites W1996941442 @default.
- W4319586100 cites W2097246321 @default.
- W4319586100 cites W2161009717 @default.
- W4319586100 cites W2904642422 @default.
- W4319586100 cites W2905029197 @default.
- W4319586100 cites W2963917042 @default.
- W4319586100 cites W2964023221 @default.
- W4319586100 cites W2973474224 @default.
- W4319586100 cites W2997837569 @default.
- W4319586100 cites W3035447285 @default.
- W4319586100 cites W3043178100 @default.
- W4319586100 cites W3082738012 @default.
- W4319586100 cites W3117178429 @default.
- W4319586100 cites W3123103757 @default.
- W4319586100 cites W3126453897 @default.
- W4319586100 cites W3161810785 @default.
- W4319586100 cites W3181414820 @default.
- W4319586100 cites W4205438669 @default.
- W4319586100 cites W4288758404 @default.
- W4319586100 doi "https://doi.org/10.1109/icdmw58026.2022.00119" @default.
- W4319586100 hasPublicationYear "2022" @default.
- W4319586100 type Work @default.
- W4319586100 citedByCount "0" @default.
- W4319586100 crossrefType "proceedings-article" @default.
- W4319586100 hasAuthorship W4319586100A5031804038 @default.
- W4319586100 hasAuthorship W4319586100A5038076471 @default.
- W4319586100 hasAuthorship W4319586100A5090913655 @default.
- W4319586100 hasConcept C119857082 @default.
- W4319586100 hasConcept C132525143 @default.
- W4319586100 hasConcept C136886441 @default.
- W4319586100 hasConcept C144024400 @default.
- W4319586100 hasConcept C144133560 @default.
- W4319586100 hasConcept C154945302 @default.
- W4319586100 hasConcept C15744967 @default.
- W4319586100 hasConcept C162324750 @default.
- W4319586100 hasConcept C162853370 @default.
- W4319586100 hasConcept C187736073 @default.
- W4319586100 hasConcept C188147891 @default.
- W4319586100 hasConcept C19165224 @default.
- W4319586100 hasConcept C197352929 @default.
- W4319586100 hasConcept C2779458634 @default.
- W4319586100 hasConcept C2780451532 @default.
- W4319586100 hasConcept C28006648 @default.
- W4319586100 hasConcept C37736160 @default.
- W4319586100 hasConcept C41008148 @default.
- W4319586100 hasConcept C59404180 @default.
- W4319586100 hasConcept C80444323 @default.
- W4319586100 hasConcept C86251818 @default.
- W4319586100 hasConceptScore W4319586100C119857082 @default.
- W4319586100 hasConceptScore W4319586100C132525143 @default.
- W4319586100 hasConceptScore W4319586100C136886441 @default.
- W4319586100 hasConceptScore W4319586100C144024400 @default.
- W4319586100 hasConceptScore W4319586100C144133560 @default.
- W4319586100 hasConceptScore W4319586100C154945302 @default.
- W4319586100 hasConceptScore W4319586100C15744967 @default.
- W4319586100 hasConceptScore W4319586100C162324750 @default.
- W4319586100 hasConceptScore W4319586100C162853370 @default.
- W4319586100 hasConceptScore W4319586100C187736073 @default.
- W4319586100 hasConceptScore W4319586100C188147891 @default.
- W4319586100 hasConceptScore W4319586100C19165224 @default.
- W4319586100 hasConceptScore W4319586100C197352929 @default.
- W4319586100 hasConceptScore W4319586100C2779458634 @default.
- W4319586100 hasConceptScore W4319586100C2780451532 @default.
- W4319586100 hasConceptScore W4319586100C28006648 @default.
- W4319586100 hasConceptScore W4319586100C37736160 @default.
- W4319586100 hasConceptScore W4319586100C41008148 @default.
- W4319586100 hasConceptScore W4319586100C59404180 @default.
- W4319586100 hasConceptScore W4319586100C80444323 @default.
- W4319586100 hasConceptScore W4319586100C86251818 @default.
- W4319586100 hasLocation W43195861001 @default.
- W4319586100 hasOpenAccess W4319586100 @default.
- W4319586100 hasPrimaryLocation W43195861001 @default.
- W4319586100 hasRelatedWork W2890607871 @default.
- W4319586100 hasRelatedWork W2908875379 @default.
- W4319586100 hasRelatedWork W3132556242 @default.
- W4319586100 hasRelatedWork W3139096754 @default.
- W4319586100 hasRelatedWork W3157905146 @default.
- W4319586100 hasRelatedWork W3202794254 @default.
- W4319586100 hasRelatedWork W4221140418 @default.
- W4319586100 hasRelatedWork W4225095221 @default.
- W4319586100 hasRelatedWork W4287027946 @default.
- W4319586100 hasRelatedWork W4319586100 @default.
- W4319586100 isParatext "false" @default.
- W4319586100 isRetracted "false" @default.
- W4319586100 workType "article" @default.