Learning Optimal Multimodal Information Bottleneck Representations
Authors: Qilong Wu, Yiyang Shao, Jun Wang, Xiaobo Sun
ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, we empirically validate the OMIB s theoretical properties on synthetic data and demonstrate its superiority over the state-of-the-art benchmark methods in various downstream tasks. |
| Researcher Affiliation | Collaboration | 1School of Statistics and Mathematics, Zhongnan University of Economics and Law 2School of Finance, Zhongnan University of Economics and Law 3i Wudao 4School of Medicine, Department of Human Genetics, Emory University. Correspondence to: Xiaobo Sun <EMAIL>. |
| Pseudocode | Yes | The algorithmic workflow of the warm-up training is described in Appendix L. The algorithmic workflow of the main training procedure is detailed in Appendix L. Appendix L contains Algorithm 1 Warm-up training and Algorithm 2 Main training. |
| Open Source Code | No | The paper does not contain any explicit statement about releasing source code for the methodology described, nor does it provide a direct link to a code repository. |
| Open Datasets | Yes | The emotion recognition experiment is conducted on CREMA-D (Cao et al., 2014)... The MSA experiment utilizes CMU-MOSI (Zadeh et al., 2016)... The pathological tissue detection experiment involves eight datasets derived from healthy human breast tissues (10x-h NB-{A-H}) and human breast cancer tissues (10x-h BC-{A-H}) (Xu et al., 2024b)... |
| Dataset Splits | Yes | SIM: We use the Adam optimizer with a learning rate of 1e-4 and train the model for 100 epochs. The dataset consists of 10,000 samples, split into training and test sets with a 9:1 ratio. CREMA-D: The dataset is divided into a training set containing 6,698 samples and a test set of 744 samples. CMU-MOSI: 2,199 utterances are extracted from the dataset, which are split into a training set (1,281 samples) and a test set (685 samples). 10x-h NB-{A-H}& 10x-h BC-{A-D}: Table 7 provides sample counts for training and test sets for these datasets. |
| Hardware Specification | No | The paper mentions: 'All experiments are implemented using Py Torch (Paszke et al., 2019), with the following settings:...' but does not specify any particular CPU or GPU models, or other hardware details used for the experiments. |
| Software Dependencies | No | The paper mentions 'All experiments are implemented using Py Torch (Paszke et al., 2019)' and 'using the SCANPY package (Wolf et al., 2018)', but it does not provide specific version numbers for these software components or other libraries used in their implementation. |
| Experiment Setup | Yes | SIM: We use the Adam optimizer with a learning rate of 1e-4 and train the model for 100 epochs. CREMA-D: The model is trained using the SGD optimizer with a batch size of 64, momentum of 0.9, and weight decay of 1e-4. The learning rate is initialized at 1e-3 and decays by a factor of 0.1 every 70 epochs, reaching a final value of 1e-4. CMU-MOSI: We employ the Adam optimizer with a learning rate of 1e-5. 10x-h NB-{A-H}& 10x-h BC-{A-D}: We use the Adam optimizer with a learning rate of 1e-4 and a weight decay of 0.1. The training batch size is set to 128. |