Cost-Effective Interactive Attention Learning with Neural Attention Processes

Authors: Jay Heo, Junhyeon Park, Hyewon Jeong, Kwang Joon Kim, Juho Lee, Eunho Yang, Sung Ju Hwang

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate IAL on various time-series datasets from multiple domains (healthcare, real-estate, and computer vision) on which it significantly outperforms baselines with conventional attention mechanisms, or without cost-effective reranking, with substantially less retraining and human-model interaction cost.
Researcher Affiliation Collaboration 1Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea 2Yonsei University College of Medicine, Seoul, South Korea 3AITRICS, Seoul, South Korea.
Pseudocode Yes Algorithm 1 Interactive Attention Learning Framework
Open Source Code Yes The source codes and all datasets used for our experiments are publicly available at https://github.com/jayheo/IAL.
Open Datasets Yes The source codes and all datasets used for our experiments are publicly available at https://github.com/jayheo/IAL.
Dataset Splits Yes For all datasets, we generate train/valid/test splits with the ratio of 70%:10%:20%.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU models, CPU types, or memory specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers.
Experiment Setup No The paper states 'Please see supplementary file for more details of the datasets, network configurations, and hyperparameters.' The main text does not include specific hyperparameter values or detailed training configurations.