FMA-ETA: Estimating Travel Time Entirely Based on FFN With Attention
This work addresses the computational inefficiency of RNNs in ETA prediction for intelligent transportation systems, offering a faster alternative while maintaining accuracy.
The authors tackled the problem of slow training and inference speed in recurrent neural network (RNN) based methods for estimated time of arrival (ETA) by proposing FMA-ETA, a framework based on feed-forward networks with multi-factor self-attention, which achieved competitive prediction accuracy with significantly better inference speed on a real-world vehicle travel dataset.
Estimated time of arrival (ETA) is one of the most important services in intelligent transportation systems and becomes a challenging spatial-temporal (ST) data mining task in recent years. Nowadays, deep learning based methods, specifically recurrent neural networks (RNN) based ones are adapted to model the ST patterns from massive data for ETA and become the state-of-the-art. However, RNN is suffering from slow training and inference speed, as its structure is unfriendly to parallel computing. To solve this problem, we propose a novel, brief and effective framework mainly based on feed-forward network (FFN) for ETA, FFN with Multi-factor self-Attention (FMA-ETA). The novel Multi-factor self-attention mechanism is proposed to deal with different category features and aggregate the information purposefully. Extensive experimental results on the real-world vehicle travel dataset show FMA-ETA is competitive with state-of-the-art methods in terms of the prediction accuracy with significantly better inference speed.