Papers › XBNet : An Extremely Boosted Neural Network

XBNet : An Extremely Boosted Neural Network

9 Jun 2021arXiv:2106.05239archive 2025-07-28

Tushar Sarkar

Neural networks have proved to be very robust at processing unstructured data like images, text, videos, and audio. However, it has been observed that their performance is not up to the mark in tabular data; hence tree-based models are preferred in such scenarios. A popular model for tabular data is boosted trees, a highly efficacious and extensively used machine learning method, and it also provides good interpretability compared to neural networks. In this paper, we describe a novel architecture XBNet, which tries to combine tree-based models with that of neural networks to create a robust architecture trained by using a novel optimization technique, Boosted Gradient Descent for Tabular Data which increases its interpretability and performance.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly DetectionBreast Cancer DetectionDiabetes PredictionFraud DetectionGeneral ClassificationNode ClassificationSurvival Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Breast Cancer Detection Breast cancer Wisconsin_class 4 XBNET Accuracy 96.49 #1 of 1 Archive leaderboard report
Breast Cancer Detection Breast cancer Wisconsin_class 4 XBNET Average Precision 0.95 #1 of 1 Archive leaderboard report
Diabetes Prediction Diabetes XBNET Accuracy 78.78 #1 of 1 Archive leaderboard report
Fraud Detection Kaggle-Credit Card Fraud Dataset XBNET Accuracy 71.33 #2 of 2 Archive leaderboard report
General Classification iris XBNET Accuracy 100 #1 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections