Paper accepted in SIGMOD 2022: NuPS: A Parameter Server for Machine Learning with Non-Uniform Parameter Access
The paper “NuPS: A Parameter Server for Machine Learning with Non-Uniform Parameter Access” by Alexander Renz-Wieland, Rainer Gemulla, Zoi Kaoudi, and Volker Markl  has been accepted at the 2022 ACM SIGMOD International Conference on Management of Data. Abstract: Parameter servers (PSs) ...
Paper accepted in PVLDB 2022: Parallel Training of Knowledge Graph Embedding Models: A Comparison of Techniques
The paper “Parallel Training of Knowledge Graph Embedding Models: A Comparison of Techniques” by Adrian Kochsiek and Rainer Gemulla has been accepted at the 2022 Proceedings of the VLDB Endowment (PVLDB). Abstract: Knowledge graph embedding (KGE) models represent the entities and relations of a ...
Open Positions: 3 PhDs/Postdocs in NLP / Web Data Integration / Machine Learning
The Data and Web Science Group [1] at the University of Mannheim invites applications for THREE PHD/POSTDOCTORAL RESEARCHERS IN NLP / WEB DATA INTEGRATION / MACHINE LEARNING Applicants should have a strong (undergraduate/graduate) degree in computer science, natural language processing, data ...
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 ...
4 DWS Papers Accepted for ACL 2020!
Four papers by DWS members have been accepted for ACL 2020, the most prestigious conference in natural language processing (NLP).
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.
OPIEC open information extraction corpus & accompanying AKBC 2019 paper released
We have released the OPIEC open information extraction corpus; its accompanying article „OPIEC: An Open Information Extraction Corpus“ by Kiril Gashteovski, Sebastian Wanner, Sven Hertling, Samuel Broscheit, and Rainer Gemulla has been accepted for publication at Automated Knowledge Base ...
Two Papers Accepted for IJCAI 2019
The Papers “Anytime Bottom-Up Rule Learning for Knowledge Graph Completion” by Christian Meilicke, Melisachew Wudage Chekol, Daniel Ruffinelli and Heiner Stuckenschmidt and “PRoFET: Predicting the Risk of Firms from Event Transcripts” by Christoph Kilian Theil, Samuel Broscheit and Heiner ...
Article accepted at ACM TODS: A Unified Framework for Frequent Sequence Mining with Subsequence Constraints
The article „A Unified Framework for Frequent Sequence Mining with Subsequence Constraints“ by Kaustubh Beedkar, Rainer Gemulla und Wim Martens has been accepted for publication in ACM Transactions on Database Systems (TODS). Abstract: Frequent sequence mining methods often make use of constraints ...