Robust Self-Supervised Multi-Instance Learning with Structure Awareness

Authors: Yejiang Wang, Yuhai Zhao, Zhengkui Wang, Meixia Wang

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Compared with state-of-the-art supervised MIL baselines, SMILES achieves average improvement of 4.9%, 4.4% in classification accuracy on 5 benchmark datasets and 20 newsgroups datasets, respectively. In addition, we show that the model is robust to the input corruption.
Researcher Affiliation Academia Yejiang Wang1, Yuhai Zhao1, Zhengkui Wang2, Meixia Wang1 1School of Computer Science and Engineering, Northeastern University, China 2Info Comm Technology Cluster, Singapore Institute of Technology, Singapore wangyejiang@stumail.neu.edu.cn, zhaoyuhai@mail.neu.edu.cn, zhengkui.wang@singaporetech.edu.sg, wangmeixia@stumail.neu.edu.cn
Pseudocode Yes Algorithm 1: SMILES. 1: input: unlabeled training data X X, batch size N, temperature τ, augmentation ratio c, encoder network frep, pre-train head network g.
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the described methodology.
Open Datasets Yes We empirically evaluate SMILES against state-of-the-art supervised multi-instance learning algorithms on five popular benchmark datasets, twenty text datasets from the 20Newsgroups corpus and three datasets for the task of biocreative text categorization (see the Appendix for detail).
Dataset Splits Yes For SMILES, we report the mean 10-fold cross validation accuracy after 5 runs followed by a linear SVM. The linear SVM is trained by applying cross validation on training data folds and the best mean accuracy is reported.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments, such as GPU or CPU models.
Software Dependencies No The paper mentions software components like 'linear SVM' and implicitly 'neural networks', but it does not specify any version numbers for these or other software dependencies.
Experiment Setup Yes We conduct experiment with the values of the number of message passing layers, the number of epochs, batch size, the parameter C of SVM, the threshold ϵ, augmentation ratio c and temperature τ in the sets {2, 4, 8, 12}, {10, 20, 40, 100}, {32, 64, 128, 256}, {10 3, . . . , 102, 103}, {0.1, . . . , 0.5}, {10%, . . . , 50%} and {0.05, 0.1, 0.2, 0.5, 1.0, 2.0} respectively. The hidden dimension of layer is set to 128.