This motivates us to consider a challenging classification problem with intrinsic cluster structures.

The descriptions of each model setup are provided in Section 8.2 . The reason is that different types of agents have distinct behavior patterns or feasibility constraints. Compared to single-stage training, the 4.0s NBA dataset to demonstrate the effect of different numbers of edge types and re-encoding gaps. More specifically, in the first case of Figure 7, for the player of the green team in the middle, the historical steps move forward quickly, while our model can successfully predict that the player will suddenly stop, since he is surrounded by many opponents and he is not carrying the ball. Such case is a very common situation in basketball games.

Multi-agent interacting systems are prevalent in the world, from purely physical systems to complicated social dynamic systems. In many applications, effective understanding of the situation and accurate trajectory prediction of interactive agents play a significant role in downstream tasks, such as decision making and planning.

This work was conducted at Microsoft.

Deep learning models have shown tremendous success over the past decade. These models show great generalization properties when tested on the same distribution as the training dataset (in-distribution generalization).

In this work we produce a framework for constructing universal function approxi-mators on graph isomorphism classes.

Time series forecasting has been a widely explored task of great importance in many applications.