Follow us on social

Latest Posts

Stay in Touch With Us

For Advertising, media partnerships, sponsorship, associations, and alliances, please connect to us below

Email
info@globaltechoutlook.com

Phone
+91 40 230 552 15

Address
540/6, 3rd Floor, Geetanjali Towers,
KPHB-6, Hyderabad 500072

Follow us on social

Globaltechoutlook

  /  Latest News   /  Advanced Graph Neural Networks are at Use for Traffic Prediction
Graph neural networks

Advanced Graph Neural Networks are at Use for Traffic Prediction

Deepmind has come up with some AI innovation in traffic prediction

By partnering with Google, DeepMind is able to bring the benefits of AI to billions of people all over the world. Graph neural networks From reuniting a speech-impaired user with his original voice, to helping users discover personalized apps, the company is applying breakthrough research to immediate real-world problems at a Google scale.

 

Google Maps

People rely on Google Maps for accurate traffic predictions and estimated times of arrival (ETAs). These are critical tools that are especially useful when you need to be routed around a traffic jam, if you need to notify friends and family that you’re running late, or if you need to leave in time to attend an important meeting. These features are also useful for businesses such as ride share companies, which use Google Maps Platform to power their services with information about pickup and drop off times, along with estimated prices based on trip duration.  Researchers at DeepMind have partnered with the Google Maps team to improve the accuracy of real time ETAs by up to 50% in places like Berlin, Jakarta, São Paulo, Sydney, Tokyo, and Washington D.C. by using advanced machine learning techniques including Graph Neural Networks.

To calculate ETAs, Google Maps analyses live traffic data for road segments around the world. While this data gives Google Maps an accurate picture of current traffic, it doesn’t account for the traffic a driver can expect to see 10, 20, or even 50 minutes into their drive. To accurately predict future traffic, Google Maps uses machine learning to combine live traffic conditions with historical traffic patterns for roads worldwide. This process is complex for a number of reasons. For example – even though rush-hour inevitably happens every morning and evening, the exact time of rush hour can vary significantly from day to day and month to month. Additional factors like road quality, speed limits, accidents, and closures can also add to the complexity of the prediction model.

DeepMind partnered with Google Maps to help improve the accuracy of their ETAs around the world. While Google Maps’ predictive ETAs have been consistently accurate for over 97% of trips, we worked with the team to minimize the remaining inaccuracies even further – sometimes by more than 50% in cities like Taichung. To do this at a global scale, it used a generalized machine learning architecture called graph neural networks that allows it to conduct spatiotemporal reasoning by incorporating relational learning biases to model the connectivity structure of real-world road networks.

 

Dividing the world’s roads into Supersegments

Deepmind divided road networks into “Supersegments” consisting of multiple adjacent segments of road that share significant traffic volume. Currently, the Google Maps traffic prediction system consists of the following components: (1) a route analyser that processes terabytes of traffic information to construct Supersegments and (2) a novel graph neural network model, which is optimised with multiple objectives and predicts the travel time for each Supersegment. The model architecture for determining optimal routes and their travel time.

 

On the road to novel machine learning architectures for traffic prediction

Deepmind’s initial proof of concept began with a straight-forward approach that used the existing traffic system as much as possible, specifically the existing segmentation of road-networks and the associated real-time data pipeline. This meant that a Supersegment covered a set of road segments, where each segment had a specific length and corresponding speed features. At first the company trained a single fully connected neural network model for every Supersegment. These initial results were promising, and demonstrated the potential in using neural networks for predicting travel time. However, given the dynamic sizes of the Supersegments, it required a separately trained neural network model for each one. To deploy this at scale, it would have to train millions of these models, which would have posed a considerable infrastructure challenge. This led the company to look into models that could handle variable length sequences, such as recurrent neural networks (RNNs). However, incorporating further structure from the road network proved difficult. Instead, it decided to use graph neural networks. In modeling traffic, the company is interested in how cars flow through a network of roads, and graph neural networks can model network dynamics and information propagation.

Deepmind’s model treats the local road network as a graph, where each route segment corresponds to a node and edges exist between segments that are consecutive on the same road or connected through an intersection. In a graph neural network, a message passing algorithm is executed where the messages and their effect on edge and node states are learned by neural networks. From this viewpoint, our super segments are road subgraphs, which were sampled at random in proportion to traffic density. A single model can therefore be trained using these sampled subgraphs, and can be deployed at scale.

Graph neural networks extend the learning bias imposed by Convolutional Neural Networks and recurrent neural networks by generalizing the concept of “proximity”, allowing us to have arbitrarily complex connections to handle not only traffic ahead or behind us, but also along adjacent and intersecting roads. In a graph neural network, adjacent nodes pass messages to each other. By keeping this structure, we impose a locality bias where nodes will find it easier to rely on adjacent nodes (this only requires one message passing step). These mechanisms allow graph neural networks to capitalize on the connectivity structure of the road network more effectively.