Learning Reduced Order Dynamics via Geometric Representations
Imran Nasim, Melanie Weber
SCML 2024
State-of-the-art approaches for Knowledge Base Completion (KBC) exploit deep neural networks trained with both false and true assertions: positive assertions are explicitly taken from the knowledge base, whereas negative ones are generated by random sampling of entities. In this paper, we argue that random sampling is not a good training strategy since it is highly likely to generate a huge number of nonsensical assertions during training, which does not provide relevant training signal to the system. Hence, it slows down the learning process and decreases accuracy. To address this issue, we propose an alternative approach called Distributional Negative Sampling that generates meaningful negative examples which are highly likely to be false. Our approach achieves a significant improvement in Mean Reciprocal Rank values amongst two different KBC algorithms in three standard academic benchmarks.
Imran Nasim, Melanie Weber
SCML 2024
Els van Herreweghen, Uta Wille
USENIX Workshop on Smartcard Technology 1999
Salvatore Certo, Anh Pham, et al.
Quantum Machine Intelligence
Aditya Malik, Nalini Ratha, et al.
CAI 2024