Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Residual Neural Processes
Authors: Byung-Jun Lee, Seunghoon Hong, Kee-Eung Kim4545-4552
AAAI 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate that the RNP shows faster convergence and better performance, both qualitatively and quantitatively. and Experimental Results Following the training method of an NP, we train on multiple realizations of the underlying data generating process. |
| Researcher Affiliation | Academia | Byung-Jun Lee,1 Seunghoon Hong,1 Kee-Eung Kim1,2 1School of Computing, KAIST, Republic of Korea 2Graduate School of AI, KAIST, Republic of Korea |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code used for experiments can be found at : https://github.com/dlqudwns/Residual-Neural-Process |
| Open Datasets | Yes | We trained and compared BLL, ANP, and RNP models on MNIST (Le Cun et al. 1998) and sub-sampled 32 32 Celeb A (Liu et al. 2015). and The functions to train are generated from a Gaussian Process with a squared exponential kernel and small likelihood noise, with hyper-parameters fixed. |
| Dataset Splits | Yes | The number of contexts and the number of targets is chosen randomly (|C|, |T| U[3, 100]). Both XC and XT are also drawn uniformly in [ 20, 20]. and We used random sizes of contexts and targets (|C|, |T| U[3, 200]). |
| Hardware Specification | No | The paper mentions 'Wall-clock time' in the experimental results but does not provide specific details about the hardware (e.g., CPU/GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'Adam optimizer' and an 'ANP structure' from a previous work, but it does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | Adam optimizer with a learning rate of 5e-5 is used throughout all experiments. and In this experiment, we used dh = 150. and dh = 250 is used in this experiment. |