Skip to yearly menu bar Skip to main content


Spotlight Talk
in
Workshop: I Can’t Believe It’s Not Better! Bridging the gap between theory and empiricism in probabilistic machine learning

Yannick Rudolph---Graph Conditional Variational Models: Too Complex for Multiagent Trajectories?

Yannick Rudolph


Abstract:

Recent advances in modeling multiagent trajectories combine graph architectures such as graph neural networks (GNNs) with conditional variational models (CVMs) such as variational RNNs (VRNNs). Originally, CVMs have been proposed to facilitate learning with multi-modal and structured data and thus seem to perfectly match the requirements of multi-modal multiagent trajectories with their structured output spaces. Empirical results of VRNNs on trajectory data support this assumption. In this paper, we revisit experiments and proposed architectures with additional rigour, ablation runs and baselines. In contrast to common belief, we show that both, historic and current results with CVMs on trajectory data are misleading. Given a neural network with a graph architecture and/or structured output function, variational autoencoding does not contribute statistically significantly to empirical performance. Instead, we show that well-known emission functions do contribute, while coming with less complexity, engineering and computation time.

Chat is not available.