Chen Z.-MYeh M.-YTEI-WEI KUO2023-06-092023-06-092021https://www.scopus.com/inward/record.uri?eid=2-s2.0-85121767828&partnerID=40&md5=2e30241e83b600bd84659768b4400523https://scholars.lib.ntu.edu.tw/handle/123456789/632320In this paper, we study the problem of embedding uncertain knowledge graphs, where each relation between entities is associated with a confidence score. Observing the existing embedding methods may discard the uncertainty information, only incorporate a specific type of score function, or cause many false-negative samples in the training, we propose the PASSLEAF framework to solve the above issues. PASSLEAF consists of two parts, one is a model that can incorporate different types of scoring functions to predict the relation confidence scores and the other is the semi-supervised learning model by exploiting both positive and negative samples associated with the estimated confidence scores. Furthermore, PASSLEAF leverages a sample pool as a relay of generated samples to further augment the semi-supervised learning. Experiment results show that our proposed framework can learn better embedding in terms of having higher accuracy in both the confidence score prediction and tail entity prediction. Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.Forecasting; Graph embeddings; Knowledge graph; Confidence score; Embedding method; Embeddings; Graph embeddings; Knowledge graphs; Learning frameworks; Negative samples; Pool-based; Semi-supervised learning; Uncertain knowledge; Supervised learningconference paper2-s2.0-85121767828