CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding
Authors: Kaiyuan Chen, Xingzhuo Guo, Yu Zhang, Jianmin Wang, Mingsheng Long
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate that by incorporating the novel design inspired by the cognitive predictive process, Cog DPM can deliver more skillful and improved results in tasks of scientific spatiotemporal field prediction. and Table 1. Numerical Evaluation of Prediction Skills on Moving MNIST and Turbulence Datasets |
| Researcher Affiliation | Academia | Katyuan Chen * 1 Xingzhuo Guo * 1 Yu Zhang 1 Jianmin Wang 1 Mingsheng Long 1 School of Software, BNRist, Tsinghua University. |
| Pseudocode | Yes | Algorithm 1 Inference Process of Cog DPM framework |
| Open Source Code | No | No explicit statement or link indicating the release of open-source code for the described methodology was found. |
| Open Datasets | Yes | We conduct experiments on the Moving MNIST dataset (Wu et al., 2021)... The turbulent flow dataset is proposed by (Rui et al., 2020)... We use the ERA5 reanalysis dataset (Hersbach et al., 2023)... We evaluate our model on the precipitation nowcasting task using the United Kingdom precipitation dataset (Ravuri et al., 2021). |
| Dataset Splits | Yes | We generate 100,000 sequences for training, 1,000 for validation and 1,000 for testing. and We use the data from 1959-01-01 to 2013-12-31 for training, 2014-01-01 to 2016-12-31 for validation, and 2017-01-01 to 2019-12-31 for testing. |
| Hardware Specification | Yes | On the ERA5 dataset, we train the model on 2 GPU cores (NVIDIA A100) for two weeks using a batch size of 16 per training step. On the turbulence flow and Moving MNIST dataset, we train the model on 1 GPU core (NVIDIA A100) for one week using a batch size of 36 per training step. |
| Software Dependencies | No | The paper mentions using Adam optimizer and L1 loss, but does not provide specific version numbers for software dependencies like Python, PyTorch, or TensorFlow. |
| Experiment Setup | Yes | The learning rate is 2 10 5, using Adam optimizer with β1 = 0.9 and β2 = 0.999. We randomly replace conditions as i.i.d. standard Gaussian noise with a probability of 10%, following the classifier-free diffusion models (Ho & Salimans, 2021). and batch size of 16 per training step |