arXiv subjects

Zhimin Tang

Publications and source records attributed to Zhimin Tang.

9 recordsLinked to original sources

arXiv2024

SiHGNN: Leveraging Properties of Semantic Graphs for Efficient HGNN Acceleration

Heterogeneous Graph Neural Networks (HGNNs) have expanded graph representation learning to heterogeneous graph fields. Recent studies have demonstrated their superior performance across various applications, including medical analysis and recommendation systems, often surpassing existing methods. However, GPUs often experience inefficiencies when executing HGNNs due to their unique and complex execution patterns. Compared to traditional Graph Neural Networks, these patterns further exacerbate irregularities in memory access. To tackle these challenges, recent studies have focused on developing domain-specific accelerators for HGNNs. Nonetheless, most of these efforts have concentrated on optimizing the datapath or scheduling data accesses, while largely overlooking the potential benefits that could be gained from leveraging the inherent properties of the semantic graph, such as its topology, layout, and generation. In this work, we focus on leveraging the properties of semantic graphs to enhance HGNN performance. First, we analyze the Semantic Graph Build (SGB) stage and identify significant opportunities for data reuse during semantic graph generation. Next, we uncover the phenomenon of buffer thrashing during the Graph Feature Processing (GFP) stage, revealing potential optimization opportunities in semantic graph layout. Furthermore, we propose a lightweight hardware accelerator frontend for HGNNs, called SiHGNN. This accelerator frontend incorporates a tree-based Semantic Graph Builder for efficient semantic graph generation and features a novel Graph Restructurer for optimizing semantic graph layouts. Experimental results show that SiHGNN enables the state-of-the-art HGNN accelerator to achieve an average performance improvement of 2.95$\times$.

cs.AR↗

arXiv2024

GDR-HGNN: A Heterogeneous Graph Neural Networks Accelerator Frontend with Graph Decoupling and Recoupling

Heterogeneous Graph Neural Networks (HGNNs) have broadened the applicability of graph representation learning to heterogeneous graphs. However, the irregular memory access pattern of HGNNs leads to the buffer thrashing issue in HGNN accelerators. In this work, we identify an opportunity to address buffer thrashing in HGNN acceleration through an analysis of the topology of heterogeneous graphs. To harvest this opportunity, we propose a graph restructuring method and map it into a hardware frontend named GDR-HGNN. GDR-HGNN dynamically restructures the graph on the fly to enhance data locality for HGNN accelerators. Experimental results demonstrate that, with the assistance of GDR-HGNN, a leading HGNN accelerator achieves an average speedup of 14.6 times and 1.78 times compared to the state-of-the-art software framework running on A100 GPU and itself, respectively.

cs.AR↗

arXiv2023

HiHGNN: Accelerating HGNNs through Parallelism and Data Reusability Exploitation

Heterogeneous graph neural networks (HGNNs) have emerged as powerful algorithms for processing heterogeneous graphs (HetGs), widely used in many critical fields. To capture both structural and semantic information in HetGs, HGNNs first aggregate the neighboring feature vectors for each vertex in each semantic graph and then fuse the aggregated results across all semantic graphs for each vertex. Unfortunately, existing graph neural network accelerators are ill-suited to accelerate HGNNs. This is because they fail to efficiently tackle the specific execution patterns and exploit the high-degree parallelism as well as data reusability inside and across the processing of semantic graphs in HGNNs. In this work, we first quantitatively characterize a set of representative HGNN models on GPU to disclose the execution bound of each stage, inter-semantic-graph parallelism, and inter-semantic-graph data reusability in HGNNs. Guided by our findings, we propose a high-performance HGNN accelerator, HiHGNN, to alleviate the execution bound and exploit the newfound parallelism and data reusability in HGNNs. Specifically, we first propose a bound-aware stage-fusion methodology that tailors to HGNN acceleration, to fuse and pipeline the execution stages being aware of their execution bounds. Second, we design an independency-aware parallel execution design to exploit the inter-semantic-graph parallelism. Finally, we present a similarity-aware execution scheduling to exploit the inter-semantic-graph data reusability. Compared to the state-of-the-art software framework running on NVIDIA GPU T4 and GPU A100, HiHGNN respectively achieves an average 41.5$\times$ and 8.6$\times$ speedup as well as 106$\times$ and 73$\times$ energy efficiency with quarter the memory bandwidth of GPU A100.

cs.AR↗

arXiv2023

AHPA: Adaptive Horizontal Pod Autoscaling Systems on Alibaba Cloud Container Service for Kubernetes

The existing resource allocation policy for application instances in Kubernetes cannot dynamically adjust according to the requirement of business, which would cause an enormous waste of resources during fluctuations. Moreover, the emergence of new cloud services puts higher resource management requirements. This paper discusses horizontal POD resources management in Alibaba Cloud Container Services with a newly deployed AI algorithm framework named AHPA -- the adaptive horizontal pod auto-scaling system. Based on a robust decomposition forecasting algorithm and performance training model, AHPA offers an optimal pod number adjustment plan that could reduce POD resources and maintain business stability. Since being deployed in April 2021, this system has expanded to multiple customer scenarios, including logistics, social networks, AI audio and video, e-commerce, etc. Compared with the previous algorithms, AHPA solves the elastic lag problem, increasing CPU usage by 10% and reducing resource cost by more than 20%. In addition, AHPA can automatically perform flexible planning according to the predicted business volume without manual intervention, significantly saving operation and maintenance costs.

cs.LG↗

arXiv2022

RobustScaler: QoS-Aware Autoscaling for Complex Workloads

Autoscaling is a critical component for efficient resource utilization with satisfactory quality of service (QoS) in cloud computing. This paper investigates proactive autoscaling for widely-used scaling-per-query applications where scaling is required for each query, such as container registry and function-as-a-service (FaaS). In these scenarios, the workload often exhibits high uncertainty with complex temporal patterns like periodicity, noises and outliers. Conservative strategies that scale out unnecessarily many instances lead to high resource costs whereas aggressive strategies may result in poor QoS. We present RobustScaler to achieve superior trade-off between cost and QoS. Specifically, we design a novel autoscaling framework based on non-homogeneous Poisson processes (NHPP) modeling and stochastically constrained optimization. Furthermore, we develop a specialized alternating direction method of multipliers (ADMM) to efficiently train the NHPP model, and rigorously prove the QoS guarantees delivered by our optimization-based proactive strategies. Extensive experiments show that RobustScaler outperforms common baseline autoscaling strategies in various real-world traces, with large margins for complex workload patterns.

cs.DC↗

arXiv2022

Automatic Sparse Connectivity Learning for Neural Networks

Since sparse neural networks usually contain many zero weights, these unnecessary network connections can potentially be eliminated without degrading network performance. Therefore, well-designed sparse neural networks have the potential to significantly reduce FLOPs and computational resources. In this work, we propose a new automatic pruning method - Sparse Connectivity Learning (SCL). Specifically, a weight is re-parameterized as an element-wise multiplication of a trainable weight variable and a binary mask. Thus, network connectivity is fully described by the binary mask, which is modulated by a unit step function. We theoretically prove the fundamental principle of using a straight-through estimator (STE) for network pruning. This principle is that the proxy gradients of STE should be positive, ensuring that mask variables converge at their minima. After finding Leaky ReLU, Softplus, and Identity STEs can satisfy this principle, we propose to adopt Identity STE in SCL for discrete mask relaxation. We find that mask gradients of different features are very unbalanced, hence, we propose to normalize mask gradients of each feature to optimize mask variable training. In order to automatically train sparse masks, we include the total number of network connections as a regularization term in our objective function. As SCL does not require pruning criteria or hyper-parameters defined by designers for network layers, the network is explored in a larger hypothesis space to achieve optimized sparse connectivity for the best performance. SCL overcomes the limitations of existing automatic pruning methods. Experimental results demonstrate that SCL can automatically learn and select important network connections for various baseline network structures. Deep learning models trained by SCL outperform the SOTA human-designed and automatic pruning methods in sparsity, accuracy, and FLOPs reduction.

cs.CV↗

arXiv2021

Top-Related Meta-Learning Method for Few-Shot Object Detection

Many meta-learning methods are proposed for few-shot detection. However, previous most methods have two main problems, poor detection APs, and strong bias because of imbalance and insufficient datasets. Previous works mainly alleviate these issues by additional datasets, multi-relation attention mechanisms and sub-modules. However, they require more cost. In this work, for meta-learning, we find that the main challenges focus on related or irrelevant semantic features between categories. Therefore, based on semantic features, we propose a Top-C classification loss (i.e., TCL-C) for classification task and a category-based grouping mechanism for category-based meta-features obtained by the meta-model. The TCL-C exploits the true-label prediction and the most likely C-1 false classification predictions to improve detection performance on few-shot classes. According to similar appearance (i.e., visual appearance, shape, and limbs etc.) and environment in which objects often appear, the category-based grouping mechanism splits categories into disjoint groups to make similar semantic features more compact between categories within a group and obtain more significant difference between groups, alleviating the strong bias problem and further improving detection APs. The whole training consists of the base model and the fine-tuning phases. According to grouping mechanism, we group the meta-features vectors obtained by meta-model, so that the distribution difference between groups is obvious, and the one within each group is less. Extensive experiments on Pascal VOC dataset demonstrate that ours which combines the TCL-C with category-based grouping significantly outperforms previous state-of-the-art methods for few-shot detection. Compared with previous competitive baseline, ours improves detection APs by almost 4% for few-shot detection.

cs.CV↗

arXiv2020

Pixel-Semantic Revise of Position Learning A One-Stage Object Detector with A Shared Encoder-Decoder

Recently, many methods have been proposed for object detection. They cannot detect objects by semantic features, adaptively. In this work, according to channel and spatial attention mechanisms, we mainly analyze that different methods detect objects adaptively. Some state-of-the-art detectors combine different feature pyramids with many mechanisms to enhance multi-level semantic information. However, they require more cost. This work addresses that by an anchor-free detector with shared encoder-decoder with attention mechanism, extracting shared features. We consider features of different levels from backbone (e.g., ResNet-50) as the basis features. Then, we feed the features into a simple module, followed by a detector header to detect objects. Meantime, we use the semantic features to revise geometric locations, and the detector is a pixel-semantic revising of position. More importantly, this work analyzes the impact of different pooling strategies (e.g., mean, maximum or minimum) on multi-scale objects, and finds the minimum pooling improve detection performance on small objects better. Compared with state-of-the-art MNC based on ResNet-101 for the standard MSCOCO 2014 baseline, our method improves detection AP of 3.8%.

cs.CV↗

arXiv2020

Video Face Recognition System: RetinaFace-mnet-faster and Secondary Search

Face recognition is widely used in the scene. However, different visual environments require different methods, and face recognition has a difficulty in complex environments. Therefore, this paper mainly experiments complex faces in the video. First, we design an image pre-processing module for fuzzy scene or under-exposed faces to enhance images. Our experimental results demonstrate that effective images pre-processing improves the accuracy of 0.11%, 0.2% and 1.4% on LFW, WIDER FACE and our datasets, respectively. Second, we propose RetinacFace-mnet-faster for detection and a confidence threshold specification for face recognition, reducing the lost rate. Our experimental results show that our RetinaFace-mnet-faster for 640*480 resolution on the Tesla P40 and single-thread improve speed of 16.7% and 70.2%, respectively. Finally, we design secondary search mechanism with HNSW to improve performance. Ours is suitable for large-scale datasets, and experimental results show that our method is 82% faster than the violent retrieval for the single-frame detection.

cs.CV↗