DWS Research | Universität Mannheim

Paper accepted in PVLDB 2020: Dynamic Parameter Allocation in Parameter Servers

The paper “Dynamic Parameter Allocation in Parameter Servers” by Alexander Renz-Wieland, Rainer Gemulla, Steffen Zeuch and Volker Markl has been accepted at the 2020 Proceedings of the VLDB Endowment (PVLDB). Abstract: To keep up with increasing dataset sizes and model complexity, distributed ...

Paper accepted for DI2KG

The paper “Intermediate Training of BERT for Product Matching” by Ralph Peeters, Christian Bizer and Goran Glavaš has been accepted for the 2nd International Workshop on Challenges and Experiences from Data Integration to Knowledge Graphs (DI2KG) held in conjunction with VLDB 2020.

Paper accepted for CIKM

The paper “Profiling Entity Matching Benchmark Tasks” by Anna Primpeli and Christian Bizer has been accepted for the 29th International Conference on Information and Knowledge Management (CIKM) which will be held online this year.

Two Contributions to the ECML/PKDD PhD Forum

Christian Schreckenberger and Sascha Marton will present their PhD Topics at the PhD Forum of ECML / PKDD 2020: Christian Schreckenberger, Christian Bartelt and Heiner Stuckenschmidt: Tree-based Learning for Dynamic Data Streams Sascha Marton, Christian Bartelt and Heiner Stuckenschmidt: Machine ...

Two New Projects on Social Impacts of AI Started

As part of a new research program for the common good-oriented handling of artificial intelligence (AI) three projects of the University of Mannheim are funded by the Baden-Württemberg Foundation.

Paper Accepted at International Journal of Production Economics

The paper Intraday Shelf Replenishment Decision Support for perishable Goods by Jakob Huber and Heiner Stuckenschmidt has been accepted by the International Journal of Production Economics (Elsevier, Impact Factor 4,998).

Paper Accepted for International Journal of Forecasting

The paper “Daily Retail Demand Forecasting Using Machine Learning with Emphasis on Calendric Special Days” by Jakob Huber and Heiner Stuckenschmidt has been accepted for the International Journal of Forecasting (Impact Factor 3.386) DOI: doi.org/10.1016/j.ijforecast.2020.02.005

Paper Accepted for IEEE ITS

The paper “Improving Smart Charging Prioritization By Predicting Electric Vehicle Departure Time” by Oliver Frendo, Nadine Gaertner and Heiner Stuckenschmidt has been accepted for IEEE Transactions on Intelligent Transportation Systems (Impact Factor 5.744)

Paper accepted at ICLR 2020: You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings

The paper “You CAN Teach an Old Dog New Tricks! On Training Knowledge Graph Embeddings” by Daniel Ruffinelli, Samuel Broscheit and Rainer Gemulla has been accepted at the 2020 International Conference of Learning Representations (ICLR). Abstract: Knowledge graph embedding (KGE) models learn ...

LibKGE knowledge graph embedding library released

LibKGE is a PyTorch-based library for efficient training, evaluation, and hyperparameter optimization of knowledge graph embeddings (KGE). It is highly configurable, easy to use, and extensible.