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.

Slides: http://ood-kdd2026.nss-research.io/wp-content/uploads/2026/08/KDD_OOD_Tutorial.pdf

Date and Time:

9th of June 1:00 – 4:00 PM

Location

402B

Schedule

Part I – Foundations

Introduction and Motivation

Problem Formulation and Settings

Benchmarks, Datasets and Metrics

Detection and Generalisation

Part II – OOD Method Families

Post-hoc Methods

Training without Outliers

Training with Outliers

Foundation-Model Approaches

Part III – Frontiers

Applications

Open Problems and Future Directions

Tutors