AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Tree in Tree: from Decision Trees to Decision Graphs

Bingzhao Zhu, Mahsa Shoaran

NeurIPS 2021 · Graph learning › Graph algorithms and clustering · approach: Continuous DAG structure learning · 1 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
Replace the decision-tree structure with a TnT decision graphstand-alone classifier · MNIST, Connect-4, Letter, Optical recognition, Pendigits, Protein, SenseIT, USPStest accuracy: MNIST: 88.59$\pm$0.14 -> 90.87$\pm$0.31; Connect-4: 77.23$\pm$0.01 -> 78.85$\pm$0.46; Letter: 86.26$\pm$0.15 -> 86.62$\pImproved
Use TnT graphs instead of decision trees as bagging estimatorsbagging ensemble · MNISTtest accuracy: 92.31$\pm$0.57 -> 93.65$\pm$0.24Improved
Use TnT graphs instead of decision trees as AdaBoost estimatorsAdaBoost ensemble · MNISTtest accuracy: 88.61 -> 88.38Hurt
Increase the number of growing/merging rounds N1 and N2 (ablation)TnT · MNISTclassification performanceImproved
Fine-tune TnT decision graphs with tree alternating optimization (ablation)TnT · multiple classification datasetsclassification accuracyImproved
Grow shared graph nodes rather than use a conventional decision treesynthetic classification task · synthetic datanumber of splits: 6 -> 4Improved

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