Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions
Authors: Huan Ma, Zongbo Han, Changqing Zhang, Huazhu Fu, Joey Tianyi Zhou, Qinghua Hu
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on both synthetic and different real-world data demonstrate the effectiveness and trustworthiness of our method on various multimodal regression tasks (e.g., temperature prediction for superconductivity, relative location prediction for CT slices, and multimodal sentiment analysis3). We conduct extensive experiments on both synthetic and real-application data, which validate the effectiveness, robustness, and reliability of the proposed model on different multimodal regression tasks (e.g., critical temperature prediction for superconductivity [15], relative location of CT slices, and human multimodal sentiment analysis). |
| Researcher Affiliation | Academia | Huan Ma College of Intelligence and Computing Tianjin University Tianjin, China; Zongbo Han College of Intelligence and Computing Tianjin University Tianjin, China; Changqing Zhang College of Intelligence and Computing Tianjin University Tianjin, China; Huazhu Fu Institute of High Performance Computing A*STAR Singapore; Joey Tianyi Zhou Institute of High Performance Computing A*STAR Singapore; Qinghua Hu College of Intelligence and Computing Tianjin University Tianjin, China |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | 3Code: https://github.com/Ma Huan AAA/Mo NIG. |
| Open Datasets | Yes | Superconductivity4 https://archive.ics.uci.edu/ml/datasets/Superconductivity; CT slices5 https://archive.ics.uci.edu/ml/datasets/CT+slices; CMU-MOSI [50] Amir Zadeh, Rowan Zellers, Eli Pincus, and Louis-Philippe Morency. MOSI: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. Co RR, 2016.; MOSEI [51] P. P. Liang, Z. Liu, A. Zadeh, and L. P. Morency. Multimodal language analysis with recurrent multistage fusion. In Meeting of the Association for Computational Linguistics, 2018. |
| Dataset Splits | Yes | In our experiment, we use 10633, 4000, and 6600 samples as training, validation, and test data, respectively. We divide the dataset into 26750/10000/16750 samples as training, validation, and test data, respectively. For CMU-MOSEI dataset, similarly to existing work, there are 16326, 1871, and 4659 samples used as the training, validation, and test data, respectively. For CMU-MOSI dataset, we use 1284, 229, and 686 samples as training, validation, and test data, respectively. |
| Hardware Specification | No | The paper does not specify the hardware used for running the experiments (e.g., specific GPU or CPU models, memory, or cloud instances). |
| Software Dependencies | No | The paper mentions using the 'Adam optimizer' but does not provide version numbers for any specific software libraries, frameworks (like TensorFlow or PyTorch), or programming languages used in the experiments. |
| Experiment Setup | Yes | The performance from our approach (with the Adam optimizer: learning rate = 1e 3 for 400 iterations) is superior to the compared methods, which is with the lowest Root Mean Squared Error (RMSE). |