paper-with-me

홈 › Papers

Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings

2022-07-11 · Adrian Kochsiek, Fritz Niesel, Rainer Gemulla

Knowledge graph embedding (KGE) models are an effective and popular approach to represent and reason with multi-relational data. Prior studies have shown that KGE models are sensitive to hyperparameter settings, however, and that suitable choices are dataset-dependent. In this paper, we explore hyperparameter optimization (HPO) for very large knowledge graphs, where the cost of evaluating individual hyperparameter configurations is excessive. Prior studies often avoided this cost by using various heuristics; e.g., by training on a subgraph or by using fewer epochs. We systematically discuss and evaluate the quality and cost savings of such heuristics and other low-cost approximation techniques. Based on our findings, we introduce GraSH, an efficient multi-fidelity HPO algorithm for large-scale KGEs that combines both graph and epoch reduction techniques and runs in multiple rounds of increasing fidelities. We conducted an experimental study and found that GraSH obtains state-of-the-art results on large graphs at a low cost (three complete training runs in total).

📄 PDF Abstract BibTeX arXiv:2207.04979

Code (2)

uma-pi1/grash 공식 구현 pytorch
uma-pi1/dist-kge pytorch

Tasks

Graph EmbeddingHyperparameter OptimizationKnowledge Graph EmbeddingKnowledge Graph EmbeddingsKnowledge GraphsLink Prediction

Methods 이 논문이 사용한 방법론

HPO In machine learning, a hyperparameter is a parameter whose value is used to control learning process, and HPO is the problem of choosing a set of optimal hyperparameters for a…

Similar Papers 제목 키워드 기반

ExperienceThinking: Constrained Hyperparameter Optimization based on Knowledge and Pruning

2019-12-02 · Chunnan Wang, Hongzhi Wang, Chang Zhou, Hanxiao Chen

Machine learning algorithms are very sensitive to the hyperparameters, and their evaluations are generally expensive. Users desperately need intelligent methods to quickly optimize hyperparameter settings according to kn…

BIG-bench Machine LearningHyperparameter OptimizationNeural Architecture Search

Rethinking of Encoder-based Warm-start Methods in Hyperparameter Optimization

2024-03-07 · Dawid Płudowski, Antoni Zajko, Anna Kozak, Katarzyna Woźnica

Effectively representing heterogeneous tabular datasets for meta-learning purposes remains an open problem. Previous approaches rely on predefined meta-features, for example, statistical measures or landmarkers. The emer…

AttributeHyperparameter OptimizationMeta-LearningRepresentation Learning

Warmstarting for Scaling Language Models

2024-11-11 · Neeratyoy Mallik, Maciej Janowski, Johannes Hog, Herilalaina Rakotoarison 외

Scaling model sizes to scale performance has worked remarkably well for the current large language models paradigm. The research and empirical findings of various scaling studies led to novel scaling results and laws tha…

Learning to Warm-Start Bayesian Hyperparameter Optimization

2017-10-17 · Jungtaek Kim, Saehoon Kim, Seungjin Choi

Hyperparameter optimization aims to find the optimal hyperparameter configuration of a machine learning model, which provides the best performance on a validation dataset. Manual search usually leads to get stuck in a lo…

Bayesian Optimizationglobal-optimizationHyperparameter OptimizationMetric Learning

Importance-Aware Scheduling for High-Dimensional Hyperparameter Optimization

2026-06-08 · Ruinan Wang, Ian Nabney, Mohammad Golbabaee arxiv

Hyperparameter Optimization (HPO) is essential for building high-performing ML/DL models, yet conventional optimizers often struggle in high-dimensional spaces where evaluations are costly and progress is diluted across …

Hyperparameter Optimization