Towards Sharper Generalization Bounds for Adversarial Contrastive Learning
Authors: Wen Wen, Han Li, Tieliang Gong, Hong Chen
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical evaluations on real-world datasets verify our theoretical findings. |
| Researcher Affiliation | Academia | 1College of Informatics, Huazhong Agricultural University, Wuhan 430070, China 2Engineering Research Center of Intelligent Technology for Agriculture, Ministry of Education, Wuhan 430070, China 3Key Laboratory of Smart Farming for Agricultural Animals, Wuhan 430070, China 4School of Computer Science and Technology, Xi an Jiaotong University, Xi an 710049, China |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described, nor does it include specific repository links or explicit code release statements. |
| Open Datasets | Yes | We use real-world datasets from UCI Machine Learning Repository1 for experiments: the Wine, A9a, Spambase, Waveform, CIFAR-10, and MNIST datasets. Statistics of datasets are provided in Table 2. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning for train/validation/test sets. |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper mentions software components like "Adam optimizer" and "Re LU activation" but does not provide specific version numbers for these or other key software dependencies. |
| Experiment Setup | Yes | All models trained by the Adam [Kingma and Ba, 2015] optimizer with the learning rate 1e-3. The ℓ PGD algorithm [Madry et al., 2018] with step size ε/5 is used to generate adversarial perturbations, where ε denotes the maximum allowable perturbation. ...minimizing the objective max θi Br(ε) ℓ {f(xi + θi)T (f(x+ i ) f(x ij))}k j=1 + λ W1 1, (6) |