Curriculum Multi-Level Learning for Imbalanced Live-Stream Recommendation

Authors: Shuodian Yu, Junqi Jin, Li Ma, Xiaofeng Gao, Xiaopeng Wu, Haiyang Xu, Jian Xu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on a live-stream production dataset demonstrate the superiority of the proposed framework.
Researcher Affiliation Collaboration 1Mo E Key Lab of Artificial Intelligence, Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China 2Alibaba Group, Beijing, China
Pseudocode Yes Algorithm 1: Training Algorithm for CMLIR
Open Source Code No The paper does not provide a statement about open-sourcing the code for the described methodology or a link to a code repository.
Open Datasets No To exploit the effectiveness of CMLIR, we conduct our experiments on a dataset collected from Taobao Live, a popular live-stream e-commerce platform with hundreds of millions of users and tens of thousands of streamers.
Dataset Splits Yes We take the first 5 days of data as the training set, and the last day is used for validation and testing.
Hardware Specification Yes All the above models are trained with Tesla T4 GPU and implemented with Tensorflow 1.14.
Software Dependencies Yes implemented with Tensorflow 1.14.
Experiment Setup Yes The loss functions are Binary Cross Entropy following backbone model. The batch size is set to 512 and the learning rate is 0.001. We use Re LU [Nair and Hinton, 2010] as the activation function for all methods. The DNN dimension of experts in MMo E and PLE are set as [128, 64] for all methods. For CMLIR, the iteration number is set as 25, the initial step size is 1.0, the adaptor coefficient η is 1.0, and the step number k in specific learning is set as 4.