Ke Liu

Haiyang Huang, Newsha Ardalani, Anna Sun et al.

Mixture-of-Experts (MoE) models have gained popularity in achieving state-of-the-art performance in a wide range of tasks in computer vision and natural language processing. They effectively expand the model capacity while incurring a minimal increase in computation cost during training. However, deploying such models for inference is difficult due to their large size and complex communication pattern. In this work, we provide a characterization of two MoE workloads, namely Language Modeling (LM) and Machine Translation (MT) and identify their sources of inefficiencies at deployment. We propose three optimization techniques to mitigate sources of inefficiencies, namely (1) Dynamic gating, (2) Expert Buffering, and (3) Expert load balancing. We show that dynamic gating improves maximum throughput by 6.21-11.23$\times$ for LM, 5.75-10.98$\times$ for MT Encoder and 2.58-5.71$\times$ for MT Decoder. It also reduces memory usage by up to 1.36$\times$ for LM and up to 1.1$\times$ for MT. We further propose Expert Buffering, a new caching mechanism that only keeps hot, active experts in GPU memory while buffering the rest in CPU memory. This reduces static memory allocation by up to 1.47$\times$. We finally propose a load balancing methodology that provides additional scalability to the workload.

Chaoyang Wang, Zhiqiang Guo, Guohui Li et al.

Due to the development of graph neural networks, graph-based representation learning methods have made great progress in recommender systems. However, data sparsity is still a challenging problem that most graph-based recommendation methods are confronted with. Recent works try to address this problem by utilizing side information. In this paper, we exploit the relevant and easily accessible textual information by advanced natural language processing (NLP) models and propose a light RGCN-based (RGCN, relational graph convolutional network) collaborative filtering method on heterogeneous graphs. Specifically, to incorporate rich textual knowledge, we utilize a pre-trained NLP model to initialize the embeddings of text nodes. Afterward, by performing a simplified RGCN-based node information propagation on the constructed heterogeneous graph, the embeddings of users and items can be adjusted with textual knowledge, which effectively alleviates the negative effects of data sparsity. Moreover, the matching function used by most graph-based representation learning methods is the inner product, which is not appropriate for the obtained embeddings that contain complex semantics. We design a predictive network that combines graph-based representation learning with neural matching function learning, and demonstrate that this architecture can bring a significant performance improvement. Extensive experiments are conducted on three publicly available datasets, and the results verify the superior performance of our method over several baselines.