Songzhu Mei

Current Approximate Graph Pattern Mining (AGPM) systems rely on uniform and static sampler allocation strategies, which result in significant computational redundancy because most regions of the sampling space contribute little to the final estimate. However, existing systems overlook this critical characteristic and fail to account for the hierarchical memory architecture of modern servers, leading to slow convergence and substantial memory access overhead. To address these challenges, we propose HierMine, a novel AGPM system designed to overcome the aforementioned drawbacks. The core contributions of HierMine include: (i) a hierarchical sampling strategy that minimizes redundant computation and accelerates convergence; (ii) a dynamic sampling adjustment mechanism that partitions the sampling space online and reallocates samplers adaptively to enhance the hierarchical strategy; (iii) an online grouping-based convergence detection technique that enables the fine-grained dynamic sampling adjustment mechanism; and (iv) a hierarchical data layout optimized for memory access efficiency. Extensive experiments show that HierMine delivers an average speedup of up to 28.9× over state-of-the-art AGPM systems such as ScaleGPM, while maintaining strong theoretical guarantees on estimation quality. It also consistently outperforms exact graph pattern mining systems, highlighting the practical benefits of our approximate approach.

Libo Zhang, Zhaoning Zhang, Xubaizhou, Rui Li, Zhiliang Tian, Songzhu Mei, Dongsheng Li. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

With the popularity of home service robots (e.g. floor sweepers), robots should be considered to have more features for older adult care. Compared to fixed home monitors with a limited field of view, fall detection with service robots is an ideal solution to keep older adults and disabled people within sight. However, the user’s actions, such as lying on the bed to sleep or slumping on the sofa to rest, cause the traditional fall detection system to generate false alarms, which disrupts the user’s family life. The present work proposed an enhanced faster R-convolutional neural network (CNN) network by incorporating temporal action sequences and fall acceleration computation, demonstrating a reduced misjudgment rate on the service robot platform. Firstly, motion images were captured to obtain the target’s motion area description and action timing at the input stage. Then, the faster R-CNN algorithm was implemented to check the suspected falls further based on the falling acceleration of the detected actions during the training phase. Finally, the proposed temporal action sequences module eliminated the action mistaken for falling. Network training and robotic platform testing demonstrated that the proposed approach distinguished between falls and false alarms, which mitigated the occurrence of false positives. On the service robot platform, experimental results showed that the FAR was 8.19 and processing time was 0.79 s.

The graph has recently enabled substantial advances in big data analysis. As graphs are increasing from billions to trillions, efficient graph processing requires large-scale distributed clusters, which have up to thousands of nodes. For big data applications of which the computation is relatively simple, while the communication, especially for imbalanced communication is the bottleneck on distributed clusters, where huge numbers of small messages are transferred through 2D-topology networks. Graph partitioning is the dominant factor to affect the performance of large-scale distributed graph processing. Current graph partitioning policies have paid extensive attention to the utilization of the power law of big graphs but failed to exploit the advanced architectural benefits of 2D topology. To address such a problem, this paper presents GraphMedia, a communication-balanced graph partitioning for distributed search at scale. The key idea of GraphMedia is a communication-balanced partitioning to balance communication based on hardware/software co-design, in which the power law of graphs would be explored to average communication among nodes, and communication would be balanced between row and column by leveraging advanced 2D-topology knowledge. We use both benchmarks and real-world graphs to validate GraphMedia. Specially, GraphMedia-based Graph500 tests on the Tianhe supercomputer are superior to the fastest systems in the latest Graph500 lists (June 2022). We finally apply GraphMedia to real-world graphs for online graph media access, which outperforms the state-of-the-art graph partitioning and graph system by orders of magnitude.

Convolutional Neural Networks (CNNs), one of the most representative algorithms of deep learning, are widely used in various artificial intelligence applications. Convolution operations often take most of the computational overhead of CNNs. The FFT-based algorithm can improve the efficiency of convolution by reducing its algorithm complexity, there are a lot of works about the high-performance implementation of FFT-based convolution on many-core CPUs. However, there is no optimization for the non-uniform memory access (NUMA) characteristics in many-core CPUs. In this paper, we present a NUMA-aware FFT-based convolution implementation on ARMv8 many-core CPUs with NUMA architectures. The implementation can reduce a number of remote memory access through the data reordering of FFT transformations and the three-level parallelization of the complex matrix multiplication. The experiment results on a ARMv8 many-core CPU with NUMA architectures demonstrate that our NUMA-aware implementation has much better performance than the state-of-the-art work in most cases.

Convolution neural networks (CNNs) have been extensively used in machine learning applications. The most time-consuming part of CNNs are convolution operations. A common approach to implementing convolution operations is to recast them as general matrix multiplication, known as the im2col+GEMM approach. There are two main drawbacks of this approach. One is that large additional memory space is required. The other is the packing on the input elements of convolution operations are not memory-efficient enough. In this paper, we present a new parallel convolution algorithm using implicit matrix multiplication on multi-core CPUs. In comparison with Im2col+GEMM, our new algorithm can reduce the memory footprints and improve the packing efficiency. The experiment results on two ARV8-based multi-core CPUs demonstrate that our new algorithm gives much better performance and scalability than the im2col+GEMM method in most cases.

At present, with the rapid development of big data processing technology, streaming data processing and real-time data analysis have gradually become new research hotspots. Both the industry and the academia have invested a lot of research into the efficient processing methods of massive data generated in the environment such as the Internet and e-commerce. Meanwhile, high-performance computing technology and supercomputers are also looking for new business growth points. The convergence of big data processing and high performance computing technology is the general trend of big data analysis in the future. This paper will give a brief overview of typical technologies in the fusion process of big data processing and high-performance computing.