Deep Multi-Dimensional Classification with Pairwise Dimension-Specific Features
Authors: Teng Huang, Bin-Bin Jia, Min-Ling Zhang
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Comparative studies with eleven real-world MDC data sets clearly validate the effectiveness of the proposed approach. Comprehensive experiments on eleven benchmark data sets show that PIST performs better than existing well-established MDC approaches. |
| Researcher Affiliation | Academia | 1School of Computer Science and Engineering, Southeast University, Nanjing 210096, China 2College of Electrical and Information Engineering, Lanzhou University of Technology, Lanzhou 730050, China 3Key Lab. of Computer Network and Information Integration (Southeast University), MOE, China |
| Pseudocode | No | The paper describes the method using prose and mathematical equations but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statement about releasing source code or a link to a code repository for the methodology described. |
| Open Datasets | Yes | In this paper, we use eleven real-world MDC data sets for experimental studies. Table 1 summarizes basic characteristics, including the number of examples (#Exam.), the number of dimensions (#Dim.), the number of labels in each dimension (#Labels/Dim.) and the number of features (#Feat.). |
| Dataset Splits | Yes | Ten-fold cross validation are conducted for all data sets where the mean metric value as well as the standard derivation are recorded for comparison. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU/CPU models or memory used for running the experiments. |
| Software Dependencies | No | The paper mentions using "LIBSVM [Chang and Lin, 2011]" for some comparing approaches initially, but later states that these were "replaced all LIBSVM implemented classifiers with the exact same multi-layer perceptron for all comparing approaches." It does not provide specific version numbers for any other software dependencies such as deep learning frameworks or programming languages. |
| Experiment Setup | Yes | The latent dimensions of label embeddings t, feature embeddings d and all hidden layers are empirically set as 32, 512 and 512, respectively. All activation functions are fixed as Re LU followed by a dropout layer [Srivastava et al., 2014] with dropping probability of 0.5. For network optimization, SGD with a batch size of 512 and momentum of 0.9 is employed. We set the learning rate as 0.1 and the weight decay as 10^-4. |