Goto

Collaborating Authors

 asshownintable1


ba4849411c8bbdd386150e5e32204198-AuthorFeedback.pdf

Neural Information Processing Systems

To test the efficiency of each component, we remove them separately (LG-ODE-no att,7 LG-ODE-no PE) and find the performances drop. This suggests that distinguishing the importance of nodes w.r.t8 time and incorporating temporal information via learnable positional encoding would benefit model performance.9 ForEqn2, we adopt the GNN model in[2]tocapture the interaction among agents.