More Like this

1. Abstract Graph Neural Networks (GNNs) have shown satisfying performance on various graph learning tasks. To achieve better fitting capability, most GNNs are with a large number of parameters, which makes these GNNs computationally expensive. Therefore, it is difficult to deploy them onto edge devices with scarce computational resources, e.g., mobile phones and wearable smart devices. Knowledge Distillation (KD) is a common solution to compress GNNs, where a light-weighted model (i.e., the student model) is encouraged to mimic the behavior of a computationally expensive GNN (i.e., the teacher GNN model). Nevertheless, most existing GNN-based KD methods lack fairness consideration. As a consequence, the student model usually inherits and even exaggerates the bias from the teacher GNN. To handle such a problem, we take initial steps towards fair knowledge distillation for GNNs. Specifically, we first formulate a novel problem of fair knowledge distillation for GNN-based teacher-student frameworks. Then we propose a principled framework named RELIANT to mitigate the bias exhibited by the student model. Notably the design of RELIANT is decoupled from any specific teacher and student model structures, and thus can be easily adapted to various GNN-based KD frameworks. We perform extensive experiments on multiple real-world datasets, which corroborates that RELIANT achieves less biased GNN knowledge distillation while maintaining high prediction utility. Open-source code can be found at https://github.com/yushundong/RELIANT.

   Dong, Yushun ; Zhang, Binichi ; Yuan, Yiling ; Zou, Na ; Wang, Qi ; Li, Jundong ( January 2023 , Proceedings of the 2023 SIAM International Conference on Data Mining (SDM))
2. Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge

   https://doi.org/10.1109/CVPR42600.2020.00656  

   Zhao, Long ; Peng, Xi ; Chen, Yuxiao ; Kapadia, Mubbasir ; Metaxas, Dimitris N. ( June 2020 , Computer Vision and Pattern Recognition)

   null (Ed.)
3. Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge

   Zhao, Long ; Peng, Xi ; Chen, Yuxiao ; Kapadia, Mubbasir ; Metaxas, Dimitris N. ( April 2020 , Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR))
4. Adapting Distilled Knowledge for Few-Shot Relation Reasoning over Knowledge Graphs

   https://doi.org/10.1137/1.9781611977172.75  

   Zhang, Yiming ; Qian, Yiyue ; Ye, Yanfang ; Zhang, Chuxu ( January 2022 , SIAM International Conference on Data Mining (SIAM SDM))
5. Construction and evaluation of a domain-specific knowledge graph for knowledge discovery

   https://doi.org/10.1108/IDD-06-2022-0054  

   Nguyen, Huyen ; Chen, Haihua ; Chen, Jiangping ; Kargozari, Kate ; Ding, Junhua ( February 2023 , Information Discovery and Delivery)

   This study aims to evaluate a method of building a biomedical knowledge graph (KG).

   This research first constructs a COVID-19 KG on the COVID-19 Open Research Data Set, covering information over six categories (i.e. disease, drug, gene, species, therapy and symptom). The construction used open-source tools to extract entities, relations and triples. Then, the COVID-19 KG is evaluated on three data-quality dimensions: correctness, relatedness and comprehensiveness, using a semiautomatic approach. Finally, this study assesses the application of the KG by building a question answering (Q&A) system. Five queries regarding COVID-19 genomes, symptoms, transmissions and therapeutics were submitted to the system and the results were analyzed.

   With current extraction tools, the quality of the KG is moderate and difficult to improve, unless more efforts are made to improve the tools for entity extraction, relation extraction and others. This study finds that comprehensiveness and relatedness positively correlate with the data size. Furthermore, the results indicate the performances of the Q&A systems built on the larger-scale KGs are better than the smaller ones for most queries, proving the importance of relatedness and comprehensiveness to ensure the usefulness of the KG.

   The KG construction process, data-quality-based and application-based evaluations discussed in this paper provide valuable references for KG researchers and practitioners to build high-quality domain-specific knowledge discovery systems.

    

   more » « less