Model Fusion for Personalized Learning

Authors: Thanh Chi Lam, Nghia Hoang, Bryan Kian Hsiang Low, Patrick Jaillet

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 4. Theoretical Analysis; 5. Experiments; The evaluation shows that the personalized model fine-tuned with limited data performs competitively to a model built on extensive data.
Researcher Affiliation Collaboration 1National University of Singapore 2AWS AI Labs, Amazon 3Massachusetts Institute of Technology.
Pseudocode No The paper describes its methods in text and does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes Our code: https://github.com/zevergreenz/model_fusion_for_personalized_learning
Open Datasets Yes 5.2. MNIST Dataset (Le Cun et al., 2010), Le Cun, Y., Cortes, C., and Burges, C. Mnist handwritten digit database. ATT Labs [Online]. Available: http://yann. lecun. com/exdb/mnist, 2, 2010. and 5.3. Movie-Len Dataset (Harper & Konstan, 2015), Harper, F. M. and Konstan, J. A. The Movie Lens datasets: History and context. ACM Transactions on Interactive Intelligent Systems (TIIS), 5(4):1 19, 2015.
Dataset Splits No The paper mentions training and testing sets for its experiments but does not explicitly describe a validation dataset split or how it was used.
Hardware Specification No The paper describes the experimental setup and results but does not provide specific hardware details such as GPU/CPU models or memory specifications used for running experiments.
Software Dependencies No The paper mentions that code is available but does not specify any software dependencies with version numbers (e.g., specific Python, PyTorch, or TensorFlow versions) that would be needed for replication.
Experiment Setup No The paper describes model architectures (e.g., '1-layer neural net with 100 hidden neurons, [1-100-1], with Re LU activation') and the few-shot learning setup, but does not provide specific hyperparameter values like learning rates, batch sizes, or optimizer settings.