Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Learning to Prompt Knowledge Transfer for Open-World Continual Learning
Authors: Yujie Li, Xin Yang, Hao Wang, Xiangkun Wang, Tianrui Li
AAAI 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results using two real-world datasets demonstrate that the proposed Pro-KT outperforms the state-of-the-art counterparts in both the detection of unknowns and the classification of knowns markedly. |
| Researcher Affiliation | Academia | Yujie Li1,3, Xin Yang1,2*, Hao Wang4, Xiangkun Wang1,2, Tianrui Li5 1Complex Laboratory of New Finance and Economics, Southwestern University of Finance and Economics 2School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics 3School of Management Science and Engineering, Southwestern University of Finance and Economics 4School of Computer Science and Engineering, Nanyang Technological University 5School of Computing and Artificial Intelligence, Southwest Jiaotong University |
| Pseudocode | No | The paper describes its method using text and mathematical equations, but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code released at https: //github.com/Yujie Li42/Pro-KT. |
| Open Datasets | Yes | We experiment on two commonly-used and publicly-available datasets, namely Split CIFAR100 (Krizhevsky, Hinton et al. 2009) and 5-datasets (Ebrahimi et al. 2020). |
| Dataset Splits | No | The paper does not explicitly mention or provide details for a 'validation' dataset split (e.g., percentages, counts, or reference to a standard validation split). It primarily discusses training and test sets. |
| Hardware Specification | No | The paper mentions using 'Res Net32 and Vi T' as backbones, which are model architectures, not hardware specifications. No specific CPU, GPU, or other hardware details are provided for the experimental setup. |
| Software Dependencies | No | The paper does not provide specific version numbers for any ancillary software, libraries, or programming languages used in the experiments. |
| Experiment Setup | No | The paper discusses model-specific parameters (M, Lp, K) in its sensitivity analysis, but it does not provide general experimental setup details such as learning rate, batch size, optimizer type, number of epochs, or other system-level training configurations used for the main results. |