AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Energy Transformer

Benjamin Hoover, Yuchen Liang, Bao Pham, Rameswar Panda, Hendrik Strobelt, Duen Horng Chau, Mohammed J Zaki, Dmitry Krotov

NeurIPS 2023 · Architectures and efficiency › Attention and transformers · approach: Attention head and block redesign · 3 citations (OpenAlex)

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
Use Energy Transformer instead of graph anomaly baselinesGraph anomaly detection · Yelp, Amazon, T-Finance, T-Social; 1% and 40% trainingMacro-F1Mixed
Use Energy Transformer instead of graph anomaly baselinesGraph anomaly detection · Yelp, Amazon, T-Finance, T-Social; 1% and 40% trainingAUCMixed
Use Energy Transformer graph classifierGraph classification · TUDatasetaccuracyMixed
Use energy-based token routing to avoid neighborhood averagingGraph anomaly detection · Graph anomaly detectionMacro-F1Improved
Use step size 0.1 rather than the traditional step size 1 (ablation)ImageNet masked image completion ET · ImageNet-1k masked image completionreconstruction qualityImproved
Include some unoccluded patches in the MSE loss (ablation)ImageNet masked image completion ET · ImageNet-1k masked image completionHN filter learningImproved
Set attention-energy beta too high (ablation)ImageNet masked image completion ET · ImageNet-1k masked image completiontraining stabilityHurt
Remove gradient clipping (ablation)ImageNet masked image completion ET · ImageNet-1k masked image completiontraining stabilityHurt
Increase learning rate with gradient clipping (ablation)ImageNet masked image completion ET · ImageNet-1k masked image completiontraining speedImproved

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