DWS Area: Data Analytics | Universität Mannheim

Paper accepted at EMNLP Findings 2023: A Benchmark for Semi-Inductive Link Prediction in Knowledge Graphs

The paper “A Benchmark for Semi-Inductive Link Prediction in Knowledge Graphs” by Adrian Kochsiek and Rainer Gemulla has been accepted at the Findings of the Association for Computational Linguistics: EMNLP 2023. Abstract: Semi-inductive link prediction (LP) in knowledge graphs (KG) is the task ...

Paper accepted at CIKM 2023: Good Intentions: Adaptive Parameter Management via Intent Signaling

The paper “Good Intentions: Adaptive Parameter Management via Intent Signaling” by Alexander Renz-Wieland, Andreas Kieslinger, Robert Gericke, Rainer Gemulla, Zoi Kaoudi, and Volker Markl has been accepted at the 2023 CIKM Conference on Information and Knowledge Management. Abstract: Model ...

Paper accepted in Repl4NLP 2023: Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction

The paper “Friendly Neighbors: Contextualized Sequence-to-Sequence Link Prediction” by Adrian Kochsiek, Apoorv Saxena, Inderjeet Nair, and Rainer Gemulla has been accepted at the 2023 Repl4NLP Workshop on Representation Learning for NLP, hosted by ACL 2023. Abstract: We propose KGT5-context, a ...

Paper accepted in ECML-PKDD 2022: Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings

The paper “Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings” by Adrian Kochsiek, Fritz Niesel, and Rainer Gemulla has been accepted at the 2022 ECML-PKDD European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in ...

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 ...

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.