TY - GEN
T1 - When Models Leave the Training Distribution
T2 - 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1, KDD 2026
AU - Seneviratne, Suranga
AU - Denipitiyage, Dishanika
AU - Chawla, Sanjay
AU - Menon, Aditya
N1 - Publisher Copyright:
© 2026 Owner/Author.
PY - 2026/8/8
Y1 - 2026/8/8
N2 - Despite their remarkable success, Deep Neural Networks (DNNs) remain challenging to deploy in critical applications due to their inability to handle out-of-distribution (OOD) data. DNNs are trained assuming training and deployment data follow the same distribution, but this assumption is often violated in practice. When encountering unfamiliar inputs, models may produce highly confident yet incorrect predictions, and in high-stakes decision-making environments, such incorrect predictions can be costly. OOD detection has thus become fundamental across deep learning, affecting applications from computer vision and NLP to security, autonomous systems, and generative models. This tutorial covers recent developments in OOD detection from both theoretical and practical perspectives, including four major categories: (1) post-hoc methods, (2) training-based methods with auxiliary outliers, (3) training methods without auxiliary outliers, and (4) foundation model-based approaches, along with recent advances in each area.
AB - Despite their remarkable success, Deep Neural Networks (DNNs) remain challenging to deploy in critical applications due to their inability to handle out-of-distribution (OOD) data. DNNs are trained assuming training and deployment data follow the same distribution, but this assumption is often violated in practice. When encountering unfamiliar inputs, models may produce highly confident yet incorrect predictions, and in high-stakes decision-making environments, such incorrect predictions can be costly. OOD detection has thus become fundamental across deep learning, affecting applications from computer vision and NLP to security, autonomous systems, and generative models. This tutorial covers recent developments in OOD detection from both theoretical and practical perspectives, including four major categories: (1) post-hoc methods, (2) training-based methods with auxiliary outliers, (3) training methods without auxiliary outliers, and (4) foundation model-based approaches, along with recent advances in each area.
KW - ood
KW - open-set
KW - out-of-distribution
KW - semantic shifts
UR - https://www.scopus.com/pages/publications/105051104950
U2 - 10.1145/3770855.3816455
DO - 10.1145/3770855.3816455
M3 - Conference contribution
AN - SCOPUS:105051104950
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 13360
EP - 13364
BT - KDD 2026 - Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2
PB - Association for Computing Machinery
Y2 - 9 August 2026 through 13 August 2026
ER -