Search Results for author: Sahar Vahdati

Found 10 papers, 0 papers with code

ProjB: An Improved Bilinear Biased ProjE model for Knowledge Graph Completion

no code implementations15 Aug 2022 Mojtaba Moattari, Sahar Vahdati, Farhana Zulkernine

Experimental results on benchmark Knowledge Graphs (KGs) such as FB15K and WN18 show that the proposed approach outperforms the state-of-the-art models in entity prediction task using linear and bilinear methods and other recent powerful ones.

Knowledge Graph Embedding Text Generation

Multiple Run Ensemble Learning with Low-Dimensional Knowledge Graph Embeddings

no code implementations11 Apr 2021 Chengjin Xu, Mojtaba Nayyeri, Sahar Vahdati, Jens Lehmann

For example, instead of training a model one time with a large embedding size of 1200, we repeat the training of the model 6 times in parallel with an embedding size of 200 and then combine the 6 separate models for testing while the overall numbers of adjustable parameters are same (6*200=1200) and the total memory footprint remains the same.

Ensemble Learning Knowledge Graph Completion +3

5* Knowledge Graph Embeddings with Projective Transformations

no code implementations8 Jun 2020 Mojtaba Nayyeri, Sahar Vahdati, Can Aykul, Jens Lehmann

Most of the embedding models designed in Euclidean geometry usually support a single transformation type - often translation or rotation, which is suitable for learning on graphs with small differences in neighboring subgraphs.

Knowledge Graph Embedding Knowledge Graph Embeddings +2

Adaptive Margin Ranking Loss for Knowledge Graph Embeddings via a Correntropy Objective Function

no code implementations9 Jul 2019 Mojtaba Nayyeri, Xiaotian Zhou, Sahar Vahdati, Hamed Shariat Yazdi, Jens Lehmann

To tackle this problem, several loss functions have been proposed recently by adding upper bounds and lower bounds to the scores of positive and negative samples.

Knowledge Graph Embeddings Knowledge Graphs +2

Soft Marginal TransE for Scholarly Knowledge Graph Completion

no code implementations27 Apr 2019 Mojtaba Nayyeri, Sahar Vahdati, Jens Lehmann, Hamed Shariat Yazdi

In this work, the TransE embedding model is reconciled for a specific link prediction task on scholarly metadata.

Link Prediction Question Answering

Cannot find the paper you are looking for? You can Submit a new open access paper.