Timezone: »
Graph neural networks have shown superior performance in a wide range of applications providing a powerful representation of graph-structured data. Recent works show that the representation can be further improved by auxiliary tasks. However, the auxiliary tasks for heterogeneous graphs, which contain rich semantic information with various types of nodes and edges, have less explored in the literature. In this paper, to learn graph neural networks on heterogeneous graphs we propose a novel self-supervised auxiliary learning method using meta paths, which are composite relations of multiple edge types. Our proposed method is learning to learn a primary task by predicting meta-paths as auxiliary tasks. This can be viewed as a type of meta-learning. The proposed method can identify an effective combination of auxiliary tasks and automatically balance them to improve the primary task. Our methods can be applied to any graph neural networks in a plug-in manner without manual labeling or additional data. The experiments demonstrate that the proposed method consistently improves the performance of link prediction and node classification on heterogeneous graphs.
Author Information
Dasol Hwang (Korea University)
Jinyoung Park (Korea University)
Sunyoung Kwon (Pusan National University)
KyungMin Kim (Seoul National University)
Jung-Woo Ha (NAVER AI, NAVER Corp.)

- Head, AI Innovation, NAVER Cloud - Research Fellow, NAVER AI Lab - Datasets and Benchmarks Co-Chair, NeurIPS 2023 - Socials Co-Chair, ICML 2023 - Socials Co-Chair, NeurIPS 2022 - BS, Seoul National University - PhD, Seoul National University
Hyunwoo Kim (Korea University)
More from the Same Authors
-
2021 : KLUE: Korean Language Understanding Evaluation »
Sungjoon Park · Jihyung Moon · Sungdong Kim · Won Ik Cho · Ji Yoon Han · Jangwon Park · Chisung Song · Junseong Kim · Youngsook Song · Taehwan Oh · Joohong Lee · Juhyun Oh · Sungwon Lyu · Younghoon Jeong · Inkwon Lee · Sangwoo Seo · Dongjun Lee · Hyunwoo Kim · Myeonghwa Lee · Seongbo Jang · Seungwon Do · Sunkyoung Kim · Kyungtae Lim · Jongwon Lee · Kyumin Park · Jamin Shin · Seonghyun Kim · Lucy Park · Alice Oh · Jung-Woo Ha · Kyunghyun Cho -
2022 : Fine-tuning Diffusion Models with Limited Data »
Taehong Moon · Moonseok Choi · Gayoung Lee · Jung-Woo Ha · Juho Lee -
2022 Poster: TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers »
Hyeong Kyu Choi · Joonmyung Choi · Hyunwoo Kim -
2022 Poster: Invertible Monotone Operators for Normalizing Flows »
Byeongkeun Ahn · Chiyoon Kim · Youngjoon Hong · Hyunwoo Kim -
2022 Poster: On Divergence Measures for Bayesian Pseudocoresets »
Balhae Kim · Jungwon Choi · Seanie Lee · Yoonho Lee · Jung-Woo Ha · Juho Lee -
2022 Poster: SageMix: Saliency-Guided Mixup for Point Clouds »
Sanghyeok Lee · Minkyu Jeon · Injae Kim · Yunyang Xiong · Hyunwoo Kim -
2021 Poster: Metropolis-Hastings Data Augmentation for Graph Neural Networks »
Hyeonjin Park · Seunghun Lee · Sihyeon Kim · Jinyoung Park · Jisu Jeong · Kyung-Min Kim · Jung-Woo Ha · Hyunwoo Kim -
2021 Poster: Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction »
Seongjun Yun · Seoyoon Kim · Junhyun Lee · Jaewoo Kang · Hyunwoo Kim -
2021 Social: ML in Korea »
Jung-Woo Ha -
2020 Social: NeurIPS 2020 Social ML in Korea »
Jung-Woo Ha -
2019 Poster: Graph Transformer Networks »
Seongjun Yun · Minbyul Jeong · Raehyun Kim · Jaewoo Kang · Hyunwoo Kim -
2017 : Posters and Coffee »
Jean-Baptiste Tristan · Yunseong Lee · Anna Veronika Dorogush · Shohei Hido · Michael Terry · Mennatullah Siam · Hidemoto Nakada · Cody Coleman · Jung-Woo Ha · Hao Zhang · Adam Stooke · Chen Meng · Christopher Kappler · Lane Schwartz · Christopher Olston · Sebastian Schelter · Minmin Sun · Daniel Kang · Waldemar Hummer · Jichan Chung · Tim Kraska · Kannan Ramchandran · Nick Hynes · Christoph Boden · Donghyun Kwak -
2017 Spotlight: Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification »
Jinseok Nam · Eneldo Loza Mencía · Hyunwoo J Kim · Johannes Fürnkranz -
2017 Poster: Overcoming Catastrophic Forgetting by Incremental Moment Matching »
Sang-Woo Lee · Jin-Hwa Kim · Jaehyun Jun · Jung-Woo Ha · Byoung-Tak Zhang -
2017 Poster: Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification »
Jinseok Nam · Eneldo Loza Mencía · Hyunwoo J Kim · Johannes Fürnkranz -
2017 Spotlight: Overcoming Catastrophic Forgetting by Incremental Moment Matching »
Sang-Woo Lee · Jin-Hwa Kim · Jaehyun Jun · Jung-Woo Ha · Byoung-Tak Zhang -
2016 : PororoQA: Cartoon Video Series Dataset for Story Understanding »
KyungMin Kim · Min-Oh Heo · Byoung-Tak Zhang