# Meta-Learning over Time for Destination Prediction Tasks

arXiv: https://arxiv.org/abs/2206.14801 · HTML: https://mlsanity.com/paper/2206.14801/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 70 references that are in the map.
- First posted on arXiv 29 Jun 2022.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks](https://mlsanity.com/paper/2106.04489/) (2021)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Bayesian Hypernetworks](https://mlsanity.com/paper/1710.04759/) (2017)
- [Recomposing the Reinforcement Learning Building Blocks with Hypernetworks](https://mlsanity.com/paper/2106.06842/) (2021)
- [Artificial Neural Networks Applied to Taxi Destination Prediction](https://mlsanity.com/paper/1508.00021/) (2015)
- [DeepIST: Deep Image-based Spatio-Temporal Network for Travel Time Estimation](https://mlsanity.com/paper/1909.05637/) (2019)
- [T-CONV: A Convolutional Neural Network For Multi-scale Taxi Trajectory Prediction](https://mlsanity.com/paper/1611.07635/) (2016)
- [Travel Time Estimation without Road Networks: An Urban Morphological Layout Representation Approach](https://mlsanity.com/paper/1907.03381/) (2019)
- [Destination Prediction Based on Partial Trajectory Data](https://mlsanity.com/paper/2004.07473/) (2020)
- [Real-Time Workload Classification during Driving using HyperNetworks](https://mlsanity.com/paper/1810.03145/) (2018)
- [STAD: Spatio-Temporal Adjustment of Traffic-Oblivious Travel-Time Estimation](https://mlsanity.com/paper/2006.09892/) (2020)
- [(Blue) Taxi Destination and Trip Time Prediction from Partial Trajectories](https://mlsanity.com/paper/1509.05257/) (2015)
- [Map Enhanced Route Travel Time Prediction using Deep Neural Networks](https://mlsanity.com/paper/1911.02623/) (2019)
- [A Hidden Markov Model for Route and Destination Prediction](https://mlsanity.com/paper/1804.03504/) (2018)
- [Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning](https://mlsanity.com/paper/2109.03062/) (2021)
- [Variational Hyper RNN for Sequence Modeling](https://mlsanity.com/paper/2002.10501/) (2020)

## Built on by (most cited first, 1 of 1)

- [MobilityDL: A Review of Deep Learning From Trajectory Data](https://mlsanity.com/paper/2402.00732/) (2024)

## Abstract (arXiv)

A need to understand and predict vehicles' behavior underlies both public and private goals in the transportation domain, including urban planning and management, ride-sharing services, and intelligent transportation systems. Individuals' preferences and intended destinations vary throughout the day, week, and year: for example, bars are most popular in the evenings, and beaches are most popular in the summer. Despite this principle, we note that recent studies on a popular benchmark dataset from Porto, Portugal have found, at best, only marginal improvements in predictive performance from incorporating temporal information. We propose an approach based on hypernetworks, a variant of meta-learning ("learning to learn") in which a neural network learns to change its own weights in response to an input. In our case, the weights responsible for destination prediction vary with the metadata, in particular the time, of the input trajectory. The time-conditioned weights notably improve the model's error relative to ablation studies and comparable prior work, and we confirm our hypothesis that knowledge of time should improve prediction of a vehicle's intended destination.