Deep Active Learning for Anchor User Prediction
Authors: Anfeng Cheng, Chuan Zhou, Hong Yang, Jia Wu, Lei Li, Jianlong Tan, Li Guo
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on real-world social network data demonstrate that DALAUP outperforms the state-of-the-art approaches. |
| Researcher Affiliation | Academia | Anfeng Cheng1,2 , Chuan Zhou1,2 , Hong Yang3 , Jia Wu4 , Lei Li5 , Jianlong Tan1,2 and Li Guo1,2 1Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China 2School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China 3Centre for Artificial Intelligence, School of Software, FEIT, University of Technology Sydney 4Department of Computing, Macquarie University, Sydney, Australia 5School of Computer Science and Information Engineering, Hefei University of Technology, China {chenganfeng, zhouchuan, tanjianlong, guoli}@iie.ac.cn, hong.yang@student.uts.edu.au, jia.wu@mq.edu.au, lilei@hfut.edu.cn |
| Pseudocode | Yes | Algorithm 1 The DALAUP algorithm |
| Open Source Code | Yes | 1https://github.com/chengaf/DALAUP |
| Open Datasets | Yes | We use Foursquare and Twitter [Kong et al., 2013] as the testbed. All the anchor user pairs are known in these data sets. |
| Dataset Splits | Yes | we first randomly split the whole anchor user data into four parts: an initial training set to build an initial model, a validate set to get the rewards of different query strategies, a test set to evaluate the performance of the model, and an unlabeled set to select user pairs [Shen et al., 2004]. The size of anchor user pairs in each part is 100, 300, 600 and 2,141 respectively. |
| Hardware Specification | No | The paper does not provide specific hardware details such as exact GPU/CPU models, processor types with speeds, or memory amounts used for running its experiments. |
| Software Dependencies | No | The paper mentions some parameter settings for models (e.g., 'window size is 5 and walks per user is 80' for Deep Walk, and 'restart probability to c = 0.6' for their method) but does not provide specific software dependencies or library names with version numbers needed to replicate the experiments. |
| Experiment Setup | Yes | The optimal parameter settings for each method are either determined by experiments or taken from the suggestions by previous works. Following [Perozzi et al., 2014], we use the default parameter setting for DW, i.e., window size is 5 and walks per user is 80. In our method, we set the restart probability to c = 0.6 [Tong et al., 2006] and the number of convolution layers k = 2. Margin ϵ in Lcross is set to 0. The other parameters are set as: λ1 = 0.01, λ2 = 0.01, λ3 = 10−5. |