207 citations · 253 across the 25 of their papers we have counts for
8 papers · 1 filter
TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data
Dayananda Herurkar, Federico Raue, Joachim Folz +2
Continual anomaly detection in tabular data is challenging and remains largely underexplored, particularly in settings with heterogeneous feature schemas, distribution shifts, and…
Tabular Data Adapters: Improving Outlier Detection for Unlabeled Private Data
Dayananda Herurkar, Jörn Hees, Vesselin Tzvetkov +1
The remarkable success of Deep Learning approaches is often based and demonstrated on large public datasets. However, when applying such approaches to internal, private datasets, o…
Explaining Anomalies using Denoising Autoencoders for Financial Tabular Data
Timur Sattarov, Dayananda Herurkar, Jörn Hees
Recent advances in Explainable AI (XAI) increased the demand for deployment of safe and interpretable AI models in various industry sectors. Despite the latest success of deep neur…
A Reinforcement Learning Approach for Sequential Spatial Transformer Networks
Fatemeh Azimi, Federico Raue, Joern Hees +1
Spatial Transformer Networks (STN) can generate geometric transformations which modify input images to improve the classifier's performance. In this work, we combine the idea of ST…
RECol: Reconstruction Error Columns for Outlier Detection
Jörn Hees, Dayananda Herurkar, Mario Meier
Detecting outliers or anomalies is a common data analysis task. As a sub-field of unsupervised machine learning, a large variety of approaches exist, but the vast majority treats t…
Contextual Classification Using Self-Supervised Auxiliary Models for Deep Neural Networks
Sebastian Palacio, Philipp Engler, Jörn Hees +1
Classification problems solved with deep neural networks (DNNs) typically rely on a closed world paradigm, and optimize over a single objective (e.g., minimization of the cross-ent…
Fusion Strategies for Learning User Embeddings with Neural Networks
Philipp Blandfort, Tushar Karayil, Federico Raue +2
Growing amounts of online user data motivate the need for automated processing techniques. In case of user ratings, one interesting option is to use neural networks for learning to…
Adversarial Defense based on Structure-to-Signal Autoencoders
Joachim Folz, Sebastian Palacio, Joern Hees +2
Adversarial attack methods have demonstrated the fragility of deep neural networks. Their imperceptible perturbations are frequently able fool classifiers into potentially dangerou…