Auto-attention mechanism for multi-view deep embedding clustering

Diallo, Bassoma; Hu, Jie; Li, Tianrui; Khan, Ghufran Ahmad; Liang, Xinyan; Wang, Hongjun

doi:10.1016/j.patcog.2023.109764

Cited by 18 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This oversight often results in the neglect of the interrelations among different multiviews. In terms of processing multi-view data, current deep learning methods need to drive different neural networks independently for different viewpoints, resulting in low efficiency and high computational resource consumption, Diallo et al [29] proposed an innovative Multi-view Deep Embedded Clustering (MDEC) model that employs a triple fusion technique designed to reduce the errors incurred in learning the features of each view and correlating data from multiple views. None of the existing methods in attributed graph clustering realize that the nonlinearity between two consecutive GCN layers is unnecessary for improving the performance of attributed graph clustering, and may even impair the efficiency of the model.…”

Section: Combine the Attention Mechanismmentioning

confidence: 99%

MAGRU: Multi-layer Attention with GRU for Logistics Warehousing Demand Prediction

2024

KSII TIIS

View full text Add to dashboard Cite

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

show abstract

Section: Combine the Attention Mechanismmentioning

confidence: 99%