动态网络表示的动量非负张量因式分解模型（英文版）

英文标题：A Momentum-Incorporated Non-Negative Latent Factorization of Tensors Model for Dynamic Network Representation中文摘要：本文提出了一种基于动量梯度下降的非线性潜在张量因子分解模型 (MNNL)，可从高维不完整张量 (HDI) 中提取非负潜在因子，改善了传统 LFT 模型的训练问题，提高了预测准确性和收敛速度。英文摘要：A large-scale dynamic network (LDN) is a source of data in many bigdata-related applications due to their large number of entities and large-scaledynamic interactions. They can be modeled as a high-dimensional incomplete(HDI) tensor that contains a wealth of knowledge about time