Modeling Attention Flow on Graphs
This work addresses the need for interpretable reasoning in complex systems, offering a method that improves both accuracy and clarity for trajectory analysis on graphs.
The paper tackled the problem of reasoning about processes on graphs, where only source and destination nodes are observed, by introducing an attention flow mechanism to model the reasoning process. The result showed that this approach provides higher prediction accuracy and better interpretation for trajectory reasoning tasks.
Real-world scenarios demand reasoning about process, more than final outcome prediction, to discover latent causal chains and better understand complex systems. It requires the learning algorithms to offer both accurate predictions and clear interpretations. We design a set of trajectory reasoning tasks on graphs with only the source and the destination observed. We present the attention flow mechanism to explicitly model the reasoning process, leveraging the relational inductive biases by basing our models on graph networks. We study the way attention flow can effectively act on the underlying information flow implemented by message passing. Experiments demonstrate that the attention flow driven by and interacting with graph networks can provide higher accuracy in prediction and better interpretation for trajectory reasoning.