AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity

Jingyuan Li, Leo Scholl, Trung Le, Pavithra Rajeswaran, Amy L Orsborn, Eli Shlizerman

NeurIPS 2023 · Probabilistic and scientific modeling › Dynamical systems · approach: Low-rank and diffusion neural dynamics

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
remove both Add and Modulator modules (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.424Hurt
remove self-connection in graph (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.427Hurt
remove Add from graph operation (keep Modulator) (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.647Hurt
remove Modulator (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.652Hurt
remove sample-dependent Adaptor from Add (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.655Hurt
keep only Adaptor in Add module (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.648Hurt
make adjacency matrix non-learnable with random init (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.575Hurt
make adjacency matrix non-learnable with correlation init (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.617Hurt
use random instead of correlation initialization with learnable adjacency (ablation)AMAG · Monkey C multi-stepR2: 0.657 -> 0.652No clear effect
use KNN pruning instead of similarity threshold 0.5 for DCRNN (ablation)DCRNN · Monkey C multi-stepR2: 0.573 -> 0.606Improved
use KNN pruning instead of similarity threshold 0.8 for DCRNN (ablation)DCRNN · Monkey C multi-stepR2: 0.445 -> 0.606Improved
use GRU-based GS4-G instead of state-space GS4-S temporal learning (ablation)GraphS4mer · Monkey M multi-stepR2: 0.181 -> 0.268Improved

Later papers that compared with this method

1 later accepted paper reports AMAG as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy