Disentangling Degree-related Biases and Interest for Out-of-Distribution Generalized Directed Network Embedding
Open Access
- 30 April 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 231-239
Abstract
The goal of directed network embedding is to represent the nodes in a given directed network as embeddings that preserve the asymmetric relationships between nodes. While a number of directed network embedding methods have been proposed, we empirically show that the existing methods lack out-of-distribution generalization abilities against degree-related distributional shifts. To mitigate this problem, we propose ODIN (Out-of-Distribution Generalized Directed Network Embedding), a new directed NE method where we model multiple factors in the formation of directed edges. Then, for each node, ODIN learns multiple embeddings, each of which preserves its corresponding factor, by disentangling interest factors and biases related to in- and out-degrees of nodes. Our experiments on four real-world directed networks demonstrate that disentangling multiple factors enables ODIN to yield out-of-distribution generalized embeddings that are consistently effective under various degrees of shifts in degree distributions. Specifically, ODIN universally outperforms 9 state-of-the-art competitors in 2 LP tasks on 4 real-world datasets under both identical distribution (ID) and non-ID settings. The code is available at https://github.com/hsyoo32/odin.Keywords
Funding Information
- Institute of Information & communications Technology Planning & Evaluation (IITP) (RS-2022-0015558, No.2022-0- 00352)
- National Research Foundation of Korea(NRF) (NRF-2022R1A6A3A03069212)
This publication has 26 references indexed in Scilit:
- THOR: Self-Supervised Temporal Knowledge Graph Embedding via Three-Tower Graph Convolutional Networks2022
- Adversarial Learning of Balanced Triangles for Accurate Community Detection on Signed Networks2021
- Towards Non-I.I.D. image classification: A dataset and baselinesPattern Recognition, 2021
- RealGraph: A Graph Engine Leveraging the Power-Law Distribution of Real-World Graphs2019
- Network Representation Learning: A SurveyIEEE Transactions on Big Data, 2018
- A Survey on Network EmbeddingIEEE Transactions on Knowledge and Data Engineering, 2018
- Structural Deep Network Embedding2016
- node2vec2016
- DeepWalk2014
- Measuring preferential attachment in evolving networksEurophysics Letters, 2003