Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310884660> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4310884660 abstract "Traditional learning-based approaches to student modeling (e.g., predicting grades based on measured activities) generalize poorly to underrepresented/minority student groups due to biases in data availability. In this paper, we propose a Multi-Layer Personalized Federated Learning (MLPFL) methodology which optimizes inference accuracy over different layers of student grouping criteria, such as by course and by demographic subgroups within each course. In our approach, personalized models for individual student subgroups are derived from a global model, which is trained in a distributed fashion via meta-gradient updates that account for subgroup heterogeneity while preserving modeling commonalities that exist across the full dataset. To evaluate our methodology, we consider case studies of two popular downstream student modeling tasks, knowledge tracing and outcome prediction, which leverage multiple modalities of student behavior (e.g., visits to lecture videos and participation on forums) in model training. Experiments on three real-world datasets from online courses demonstrate that our approach obtains substantial improvements over existing student modeling baselines in terms of increasing the average and decreasing the variance of prediction quality across different student subgroups. Visual analysis of the resulting students' knowledge state embeddings confirm that our personalization methodology extracts activity patterns which cluster into different student subgroups, consistent with the performance enhancements we obtain over the baselines." @default.
- W4310884660 created "2022-12-20" @default.
- W4310884660 creator A5000769601 @default.
- W4310884660 creator A5020399355 @default.
- W4310884660 creator A5034650819 @default.
- W4310884660 creator A5049462632 @default.
- W4310884660 creator A5063813962 @default.
- W4310884660 creator A5074403000 @default.
- W4310884660 creator A5090537862 @default.
- W4310884660 date "2022-12-05" @default.
- W4310884660 modified "2023-10-14" @default.
- W4310884660 title "Multi-Layer Personalized Federated Learning for Mitigating Biases in Student Predictive Analytics" @default.
- W4310884660 doi "https://doi.org/10.48550/arxiv.2212.02985" @default.
- W4310884660 hasPublicationYear "2022" @default.
- W4310884660 type Work @default.
- W4310884660 citedByCount "0" @default.
- W4310884660 crossrefType "posted-content" @default.
- W4310884660 hasAuthorship W4310884660A5000769601 @default.
- W4310884660 hasAuthorship W4310884660A5020399355 @default.
- W4310884660 hasAuthorship W4310884660A5034650819 @default.
- W4310884660 hasAuthorship W4310884660A5049462632 @default.
- W4310884660 hasAuthorship W4310884660A5063813962 @default.
- W4310884660 hasAuthorship W4310884660A5074403000 @default.
- W4310884660 hasAuthorship W4310884660A5090537862 @default.
- W4310884660 hasBestOaLocation W43108846601 @default.
- W4310884660 hasConcept C119857082 @default.
- W4310884660 hasConcept C136764020 @default.
- W4310884660 hasConcept C142039133 @default.
- W4310884660 hasConcept C144024400 @default.
- W4310884660 hasConcept C145420912 @default.
- W4310884660 hasConcept C15122004 @default.
- W4310884660 hasConcept C153083717 @default.
- W4310884660 hasConcept C154945302 @default.
- W4310884660 hasConcept C15744967 @default.
- W4310884660 hasConcept C183003079 @default.
- W4310884660 hasConcept C2522767166 @default.
- W4310884660 hasConcept C2776214188 @default.
- W4310884660 hasConcept C2777648619 @default.
- W4310884660 hasConcept C2779903281 @default.
- W4310884660 hasConcept C36289849 @default.
- W4310884660 hasConcept C41008148 @default.
- W4310884660 hasConcept C51672120 @default.
- W4310884660 hasConcept C79158427 @default.
- W4310884660 hasConcept C88610354 @default.
- W4310884660 hasConceptScore W4310884660C119857082 @default.
- W4310884660 hasConceptScore W4310884660C136764020 @default.
- W4310884660 hasConceptScore W4310884660C142039133 @default.
- W4310884660 hasConceptScore W4310884660C144024400 @default.
- W4310884660 hasConceptScore W4310884660C145420912 @default.
- W4310884660 hasConceptScore W4310884660C15122004 @default.
- W4310884660 hasConceptScore W4310884660C153083717 @default.
- W4310884660 hasConceptScore W4310884660C154945302 @default.
- W4310884660 hasConceptScore W4310884660C15744967 @default.
- W4310884660 hasConceptScore W4310884660C183003079 @default.
- W4310884660 hasConceptScore W4310884660C2522767166 @default.
- W4310884660 hasConceptScore W4310884660C2776214188 @default.
- W4310884660 hasConceptScore W4310884660C2777648619 @default.
- W4310884660 hasConceptScore W4310884660C2779903281 @default.
- W4310884660 hasConceptScore W4310884660C36289849 @default.
- W4310884660 hasConceptScore W4310884660C41008148 @default.
- W4310884660 hasConceptScore W4310884660C51672120 @default.
- W4310884660 hasConceptScore W4310884660C79158427 @default.
- W4310884660 hasConceptScore W4310884660C88610354 @default.
- W4310884660 hasLocation W43108846601 @default.
- W4310884660 hasLocation W43108846602 @default.
- W4310884660 hasOpenAccess W4310884660 @default.
- W4310884660 hasPrimaryLocation W43108846601 @default.
- W4310884660 hasRelatedWork W2234248442 @default.
- W4310884660 hasRelatedWork W2331775400 @default.
- W4310884660 hasRelatedWork W2504091800 @default.
- W4310884660 hasRelatedWork W2592276701 @default.
- W4310884660 hasRelatedWork W2768832457 @default.
- W4310884660 hasRelatedWork W2788568090 @default.
- W4310884660 hasRelatedWork W3097749327 @default.
- W4310884660 hasRelatedWork W4214816265 @default.
- W4310884660 hasRelatedWork W4294350028 @default.
- W4310884660 hasRelatedWork W605203981 @default.
- W4310884660 isParatext "false" @default.
- W4310884660 isRetracted "false" @default.
- W4310884660 workType "article" @default.