Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Jan 202019922001200920172026
3 results for “PyKEEN”
PyKEEN 1.0: A Python Library for Training and Evaluating Knowledge Graph Embeddingscs.LG

PyKEEN 1.0 simplifies KGE model creation and optimization.

problem Training and evaluating knowledge graph embeddings (KGEs).
method Composes KGEMs with various interaction models, training approaches, and loss functions. Implements automatic memory optimization and extensive HPO functionalities.
result PyKEEN 1.0 streamlines KGE model creation and optimization.
knowledge graph embeddingsknowledge graphembedding modelstraining approachesloss functions
2020-07-28abs ↗pdf ↗
Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Frameworkcs.LG

Study evaluates 21 KG embedding models, highlighting model architecture, training approach, and loss function importance.

problem Difficulty in fair and thorough comparisons of knowledge graph embedding models due to heterogeneity in implementations, training, and evaluation.
method Reimplemented and evaluated 21 models in PyKEEN, providing insights into reproducibility and best practices.
result Best practices and configurations for each model were identified, showing the importance of model architecture, training approach, and loss function.
knowledge graph embeddingmodel evaluationreproducibilityPyKEENbest practices
2020-06-23abs ↗pdf ↗