Circulant Maximum Variance Bases -- Quantified Boolean Solving for Achievement Games -- Knowledge Graph Based Question Answering System for Financial Securities -- Semi-unsupervised Learning: An In-depth Parameter Analysis -- Combining Transformer Generators with Convolutional Discriminators -- Explanation as a process: user-centric construction of multi-level and multi-modal explanations -- Multi-Type-TD-TSR - Extracting Tables from Document Images using a Multi-stage Pipeline for Table Detection and Table Structure Recognition: from OCR to Structured Table Representations -- A high-speed neural architecture search considering the number of weights -- Semantic Segmentation of Aerial Images using Binary Space Partitioning -- EVARS-GPR: EVent-triggered Augmented Refitting of Gaussian Process Regression for Seasonal Data -- Selective Pseudo-label Clustering -- Crop it, but not too much: the effects of mask-based image preprocessing on the classification of skin lesions . . . . A Demonstrator for Interactive Image Clustering and Fine-Tuning Neural Networks in Virtual Reality -- HUI-Audio-Corpus-German: A high quality TTS dataset -- Negation in Cognitive Reasoning -- Learning to Detect Adversarial Examples Based on Class Scores -- An agent architecture for knowledge discovery and evolution -- Demystifying Artificial Intelligence for End-Users: Findings from a Participatory Machine Learning Show -- Recent Advances in Counting and Sampling Markov Equivalent DAGs -- Approach to Reduce the Number of Conditional Independence Tests in the PC Algorithm -- Unsupervised Anomaly Detection for Financial Auditing with Model-Agnostic Explanations -- Approximation of Symmetries in Dynamic Probabilistic Relational Models -- Towards More Explicit Interaction Modelling in Agent-Based Simulation Using Affordance Schemata -- Critic Guided Segmentation of Rewarding Objects in First-Person Views.-Self-Supervised Domain Adaptation for Diabetic Retinopathy Grading using Vessel Image Reconstruction -- BehavE: Behaviour Understanding through Automated Generation of Situation Models.

This book constitutes the refereed proceedings of the 44th German Conference on Artificial Intelligence, KI 2021, held in September/October 2021. Due to COVID-19 pandemic the conference was held virtually. The 16 full and 4 short papers with one extended abstract were carefully reviewed and selected from 59 submissions. As well-established annual conference series KI is dedicated to research on theory and applications across all methods and topic areas of AI research.