PyTorchKR Papers

최신 논문

총 5,576편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2304.07948

Sustainable AIGC Workload Scheduling of Geo-Distributed Data Centers: A Multi-Agent Reinforcement Learning Approach

Recent breakthroughs in generative artificial intelligence have triggered a surge in demand for machine learning training, which poses significant cost burdens and environmental challenges due to its substantial energy consumption. Scheduling training jobs among geographically distributed cloud data centers unveils the opportunity to optimize the usage of computing capacity powered by inexpensive and low-carbon energy and address the issue of workload imbalance. To tackle the challenge of multi-objective scheduling, i.e., maximizing GPU utilization while reducing operational costs, we propose an algorithm based on multi-agent reinforcement learning and actor-critic methods to learn the optimal collaborative scheduling strategy through interacting with a cloud system built with real-life workload patterns, energy prices, and carbon intensities. Compared with other algorithms, our proposed method improves the system utility by up to 28.6% attributable to higher GPU utilization, lower energy cost, and less carbon emission.

arXiv:2304.08480공식 코드 · Papers with Code

DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training

We propose DisCo-CLIP, a distributed memory-efficient CLIP training approach, to reduce the memory consumption of contrastive loss when training contrastive learning models. Our approach decomposes the contrastive loss and its gradient computation into two parts, one to calculate the intra-GPU gradients and the other to compute the inter-GPU gradients. According to our decomposition, only the intra-GPU gradients are computed on the current GPU, while the inter-GPU gradients are collected via all_reduce from other GPUs instead of being repeatedly computed on every GPU. In this way, we can reduce the GPU memory consumption of contrastive loss computation from $\bigO(B^2)$ to $\bigO(\frac{B^2}{N})$, where $B$ and $N$ are the batch size and the number of GPUs used for training. Such a distributed solution is mathematically equivalent to the original non-distributed contrastive loss computation, without sacrificing any computation accuracy. It is particularly efficient for large-batch CLIP training. For instance, DisCo-CLIP can enable contrastive training of a ViT-B/32 model with a batch size of 32K or 196K using 8 or 64 A100 40GB GPUs, compared with the original CLIP solution which requires 128 A100 40GB GPUs to train a ViT-B/32 model with a batch size of 32K. The code will be released at https://github.com/IDEA-Research/DisCo-CLIP

arXiv:2304.08069공식 코드 · Papers with Code

DETRs Beat YOLOs on Real-time Object Detection

The YOLO series has become the most popular framework for real-time object detection due to its reasonable trade-off between speed and accuracy. However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. Recently, end-to-end Transformer-based detectors (DETRs) have provided an alternative to eliminating NMS. Nevertheless, the high computational cost limits their practicality and hinders them from fully exploiting the advantage of excluding NMS. In this paper, we propose the Real-Time DEtection TRansformer (RT-DETR), the first real-time end-to-end object detector to our best knowledge that addresses the above dilemma. We build RT-DETR in two steps, drawing on the advanced DETR: first we focus on maintaining accuracy while improving speed, followed by maintaining speed while improving accuracy. Specifically, we design an efficient hybrid encoder to expeditiously process multi-scale features by decoupling intra-scale interaction and cross-scale fusion to improve speed. Then, we propose the uncertainty-minimal query selection to provide high-quality initial queries to the decoder, thereby improving accuracy. In addition, RT-DETR supports flexible speed tuning by adjusting the number of decoder layers to adapt to various scenarios without retraining. Our RT-DETR-R50 / R101 achieves 53.1% / 54.3% AP on COCO and 108 / 74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy. We also develop scaled RT-DETRs that outperform the lighter YOLO detectors (S and M models). Furthermore, RT-DETR-R50 outperforms DINO-R50 by 2.2% AP in accuracy and about 21 times in FPS. After pre-training with Objects365, RT-DETR-R50 / R101 achieves 55.3% / 56.2% AP. The project page: https://zhao-yian.github.io/RTDETR.

arXiv:2304.06987

Unsupervised ANN-Based Equalizer and Its Trainable FPGA Implementation

In recent years, communication engineers put strong emphasis on artificial neural network (ANN)-based algorithms with the aim of increasing the flexibility and autonomy of the system and its components. In this context, unsupervised training is of special interest as it enables adaptation without the overhead of transmitting pilot symbols. In this work, we present a novel ANN-based, unsupervised equalizer and its trainable field programmable gate array (FPGA) implementation. We demonstrate that our custom loss function allows the ANN to adapt for varying channel conditions, approaching the performance of a supervised baseline. Furthermore, as a first step towards a practical communication system, we design an efficient FPGA implementation of our proposed algorithm, which achieves a throughput in the order of Gbit/s, outperforming a high-performance GPU by a large margin.

arXiv:2304.07065공식 코드 · Papers with Code

SEA: A Scalable Entity Alignment System

Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). State-of-the-art EA approaches generally use Graph Neural Networks (GNNs) to encode entities. However, most of them train the models and evaluate the results in a fullbatch fashion, which prohibits EA from being scalable on largescale datasets. To enhance the usability of GNN-based EA models in real-world applications, we present SEA, a scalable entity alignment system that enables to (i) train large-scale GNNs for EA, (ii) speed up the normalization and the evaluation process, and (iii) report clear results for users to estimate different models and parameter settings. SEA can be run on a computer with merely one graphic card. Moreover, SEA encompasses six state-of-the-art EA models and provides access for users to quickly establish and evaluate their own models. Thus, SEA allows users to perform EA without being involved in tedious implementations, such as negative sampling and GPU-accelerated evaluation. With SEA, users can gain a clear view of the model performance. In the demonstration, we show that SEA is user-friendly and is of high scalability even on computers with limited computational resources.

arXiv:2304.06831공식 코드 · Papers with Code

DGNN-Booster: A Generic FPGA Accelerator Framework For Dynamic Graph Neural Network Inference

Dynamic Graph Neural Networks (DGNNs) are becoming increasingly popular due to their effectiveness in analyzing and predicting the evolution of complex interconnected graph-based systems. However, hardware deployment of DGNNs still remains a challenge. First, DGNNs do not fully utilize hardware resources because temporal data dependencies cause low hardware parallelism. Additionally, there is currently a lack of generic DGNN hardware accelerator frameworks, and existing GNN accelerator frameworks have limited ability to handle dynamic graphs with changing topologies and node features. To address the aforementioned challenges, in this paper, we propose DGNN-Booster, which is a novel Field-Programmable Gate Array (FPGA) accelerator framework for real-time DGNN inference using High-Level Synthesis (HLS). It includes two different FPGA accelerator designs with different dataflows that can support the most widely used DGNNs. We showcase the effectiveness of our designs by implementing and evaluating two representative DGNN models on ZCU102 board and measuring the end-to-end performance. The experiment results demonstrate that DGNN-Booster can achieve a speedup of up to 5.6x compared to the CPU baseline (6226R), 8.4x compared to the GPU baseline (A6000) and 2.1x compared to the FPGA baseline without applying optimizations proposed in this paper. Moreover, DGNN-Booster can achieve over 100x and over 1000x runtime energy efficiency than the CPU and GPU baseline respectively. Our implementation code and on-board measurements are publicly available at https://github.com/sharc-lab/DGNN-Booster.

arXiv:2304.06370공식 코드 · Papers with Code

Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-Attention

Driver Monitoring Systems (DMSs) are crucial for safe hand-over actions in Level-2+ self-driving vehicles. State-of-the-art DMSs leverage multiple sensors mounted at different locations to monitor the driver and the vehicle's interior scene and employ decision-level fusion to integrate these heterogenous data. However, this fusion method may not fully utilize the complementarity of different data sources and may overlook their relative importance. To address these limitations, we propose a novel multiview multimodal driver monitoring system based on feature-level fusion through multi-head self-attention (MHSA). We demonstrate its effectiveness by comparing it against four alternative fusion strategies (Sum, Conv, SE, and AFF). We also present a novel GPU-friendly supervised contrastive learning framework SuMoCo to learn better representations. Furthermore, We fine-grained the test split of the DAD dataset to enable the multi-class recognition of drivers' activities. Experiments on this enhanced database demonstrate that 1) the proposed MHSA-based fusion method (AUC-ROC: 97.0\%) outperforms all baselines and previous approaches, and 2) training MHSA with patch masking can improve its robustness against modality/view collapses. The code and annotations are publicly available.

arXiv:2304.06274

EWT: Efficient Wavelet-Transformer for Single Image Denoising

Transformer-based image denoising methods have achieved encouraging results in the past year. However, it must uses linear operations to model long-range dependencies, which greatly increases model inference time and consumes GPU storage space. Compared with convolutional neural network-based methods, current Transformer-based image denoising methods cannot achieve a balance between performance improvement and resource consumption. In this paper, we propose an Efficient Wavelet Transformer (EWT) for image denoising. Specifically, we use Discrete Wavelet Transform (DWT) and Inverse Wavelet Transform (IWT) for downsampling and upsampling, respectively. This method can fully preserve the image features while reducing the image resolution, thereby greatly reducing the device resource consumption of the Transformer model. Furthermore, we propose a novel Dual-stream Feature Extraction Block (DFEB) to extract image features at different levels, which can further reduce model inference time and GPU memory usage. Experiments show that our method speeds up the original Transformer by more than 80%, reduces GPU memory usage by more than 60%, and achieves excellent denoising results. All code will be public.

arXiv:2304.06717

Representing Volumetric Videos as Dynamic MLP Maps

This paper introduces a novel representation of volumetric videos for real-time view synthesis of dynamic scenes. Recent advances in neural scene representations demonstrate their remarkable capability to model and render complex static scenes, but extending them to represent dynamic scenes is not straightforward due to their slow rendering speed or high storage cost. To solve this problem, our key idea is to represent the radiance field of each frame as a set of shallow MLP networks whose parameters are stored in 2D grids, called MLP maps, and dynamically predicted by a 2D CNN decoder shared by all frames. Representing 3D scenes with shallow MLPs significantly improves the rendering speed, while dynamically predicting MLP parameters with a shared 2D CNN instead of explicitly storing them leads to low storage cost. Experiments show that the proposed approach achieves state-of-the-art rendering quality on the NHR and ZJU-MoCap datasets, while being efficient for real-time rendering with a speed of 41.7 fps for $512 \times 512$ images on an RTX 3090 GPU. The code is available at https://zju3dv.github.io/mlp_maps/.

arXiv:2304.05818

Gradient-Free Textual Inversion

Recent works on personalized text-to-image generation usually learn to bind a special token with specific subjects or styles of a few given images by tuning its embedding through gradient descent. It is natural to question whether we can optimize the textual inversions by only accessing the process of model inference. As only requiring the forward computation to determine the textual inversion retains the benefits of less GPU memory, simple deployment, and secure access for scalable models. In this paper, we introduce a \emph{gradient-free} framework to optimize the continuous textual inversion in an iterative evolutionary strategy. Specifically, we first initialize an appropriate token embedding for textual inversion with the consideration of visual and text vocabulary information. Then, we decompose the optimization of evolutionary strategy into dimension reduction of searching space and non-convex gradient-free optimization in subspace, which significantly accelerates the optimization process with negligible performance loss. Experiments in several applications demonstrate that the performance of text-to-image model equipped with our proposed gradient-free method is comparable to that of gradient-based counterparts with variant GPU/CPU platforms, flexible employment, as well as computational efficiency.

arXiv:2304.04344공식 코드 · Papers with Code

Towards Real-time Text-driven Image Manipulation with Unconditional Diffusion Models

Recent advances in diffusion models enable many powerful instruments for image editing. One of these instruments is text-driven image manipulations: editing semantic attributes of an image according to the provided text description. % Popular text-conditional diffusion models offer various high-quality image manipulation methods for a broad range of text prompts. Existing diffusion-based methods already achieve high-quality image manipulations for a broad range of text prompts. However, in practice, these methods require high computation costs even with a high-end GPU. This greatly limits potential real-world applications of diffusion-based image editing, especially when running on user devices. In this paper, we address efficiency of the recent text-driven editing methods based on unconditional diffusion models and develop a novel algorithm that learns image manipulations 4.5-10 times faster and applies them 8 times faster. We carefully evaluate the visual quality and expressiveness of our approach on multiple datasets using human annotators. Our experiments demonstrate that our algorithm achieves the quality of much more expensive methods. Finally, we show that our approach can adapt the pretrained model to the user-specified image and text description on the fly just for 4 seconds. In this setting, we notice that more compact unconditional diffusion models can be considered as a rational alternative to the popular text-conditional counterparts.

arXiv:2304.04297

AI-assisted Automated Workflow for Real-time X-ray Ptychography Data Analysis via Federated Resources

We present an end-to-end automated workflow that uses large-scale remote compute resources and an embedded GPU platform at the edge to enable AI/ML-accelerated real-time analysis of data collected for x-ray ptychography. Ptychography is a lensless method that is being used to image samples through a simultaneous numerical inversion of a large number of diffraction patterns from adjacent overlapping scan positions. This acquisition method can enable nanoscale imaging with x-rays and electrons, but this often requires very large experimental datasets and commensurately high turnaround times, which can limit experimental capabilities such as real-time experimental steering and low-latency monitoring. In this work, we introduce a software system that can automate ptychography data analysis tasks. We accelerate the data analysis pipeline by using a modified version of PtychoNN -- an ML-based approach to solve phase retrieval problem that shows two orders of magnitude speedup compared to traditional iterative methods. Further, our system coordinates and overlaps different data analysis tasks to minimize synchronization overhead between different stages of the workflow. We evaluate our workflow system with real-world experimental workloads from the 26ID beamline at Advanced Photon Source and ThetaGPU cluster at Argonne Leadership Computing Resources.

arXiv:2304.04567

ADS_UNet: A Nested UNet for Histopathology Image Segmentation

The UNet model consists of fully convolutional network (FCN) layers arranged as contracting encoder and upsampling decoder maps. Nested arrangements of these encoder and decoder maps give rise to extensions of the UNet model, such as UNete and UNet++. Other refinements include constraining the outputs of the convolutional layers to discriminate between segment labels when trained end to end, a property called deep supervision. This reduces feature diversity in these nested UNet models despite their large parameter space. Furthermore, for texture segmentation, pixel correlations at multiple scales contribute to the classification task; hence, explicit deep supervision of shallower layers is likely to enhance performance. In this paper, we propose ADS UNet, a stage-wise additive training algorithm that incorporates resource-efficient deep supervision in shallower layers and takes performance-weighted combinations of the sub-UNets to create the segmentation model. We provide empirical evidence on three histopathology datasets to support the claim that the proposed ADS UNet reduces correlations between constituent features and improves performance while being more resource efficient. We demonstrate that ADS_UNet outperforms state-of-the-art Transformer-based models by 1.08 and 0.6 points on CRAG and BCSS datasets, and yet requires only 37% of GPU consumption and 34% of training time as that required by Transformers.

arXiv:2304.04600공식 코드 · Papers with Code

Rotation-Scale Equivariant Steerable Filters

Incorporating either rotation equivariance or scale equivariance into CNNs has proved to be effective in improving models' generalization performance. However, jointly integrating rotation and scale equivariance into CNNs has not been widely explored. Digital histology imaging of biopsy tissue can be captured at arbitrary orientation and magnification and stored at different resolutions, resulting in cells appearing in different scales. When conventional CNNs are applied to histopathology image analysis, the generalization performance of models is limited because 1) a part of the parameters of filters are trained to fit rotation transformation, thus decreasing the capability of learning other discriminative features; 2) fixed-size filters trained on images at a given scale fail to generalize to those at different scales. To deal with these issues, we propose the Rotation-Scale Equivariant Steerable Filter (RSESF), which incorporates steerable filters and scale-space theory. The RSESF contains copies of filters that are linear combinations of Gaussian filters, whose direction is controlled by directional derivatives and whose scale parameters are trainable but constrained to span disjoint scales in successive layers of the network. Extensive experiments on two gland segmentation datasets demonstrate that our method outperforms other approaches, with much fewer trainable parameters and fewer GPU resources required. The source code is available at: https://github.com/ynulonger/RSESF.

arXiv:2304.03487

ParaGraph: Weighted Graph Representation for Performance Optimization of HPC Kernels

GPU-based HPC clusters are attracting more scientific application developers due to their extensive parallelism and energy efficiency. In order to achieve portability among a variety of multi/many core architectures, a popular choice for an application developer is to utilize directive-based parallel programming models, such as OpenMP. However, even with OpenMP, the developer must choose from among many strategies for exploiting a GPU or a CPU. Recently, Machine Learning (ML) approaches have brought significant advances in the optimizations of HPC applications. To this end, several ways have been proposed to represent application characteristics for ML models. However, the available techniques fail to capture features that are crucial for exposing parallelism. In this paper, we introduce a new graph-based program representation for parallel applications that extends the Abstract Syntax Tree to represent control and data flow information. The originality of this work lies in the addition of new edges exploiting the implicit ordering and parent-child relationships in ASTs, as well as the introduction of edge weights to account for loop and condition information. We evaluate our proposed representation by training a Graph Neural Network (GNN) to predict the runtime of an OpenMP code region across CPUs and GPUs. Various transformations utilizing collapse and data transfer between the CPU and GPU are used to construct the dataset. The predicted runtime of the model is used to determine which transformation provides the best performance. Results show that our approach is indeed effective and has normalized RMSE as low as 0.004 to at most 0.01 in its runtime predictions.

arXiv:2304.03388

EZClone: Improving DNN Model Extraction Attack via Shape Distillation from GPU Execution Profiles

Deep Neural Networks (DNNs) have become ubiquitous due to their performance on prediction and classification problems. However, they face a variety of threats as their usage spreads. Model extraction attacks, which steal DNNs, endanger intellectual property, data privacy, and security. Previous research has shown that system-level side-channels can be used to leak the architecture of a victim DNN, exacerbating these risks. We propose two DNN architecture extraction techniques catering to various threat models. The first technique uses a malicious, dynamically linked version of PyTorch to expose a victim DNN architecture through the PyTorch profiler. The second, called EZClone, exploits aggregate (rather than time-series) GPU profiles as a side-channel to predict DNN architecture, employing a simple approach and assuming little adversary capability as compared to previous work. We investigate the effectiveness of EZClone when minimizing the complexity of the attack, when applied to pruned models, and when applied across GPUs. We find that EZClone correctly predicts DNN architectures for the entire set of PyTorch vision architectures with 100% accuracy. No other work has shown this degree of architecture prediction accuracy with the same adversarial constraints or using aggregate side-channel information. Prior work has shown that, once a DNN has been successfully cloned, further attacks such as model evasion or model inversion can be accelerated significantly.

arXiv:2304.03708

Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge

Efficient automatic segmentation of multi-level (i.e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications. However, most existing methods concentrate only on main PA or branch PA segmentation separately and ignore segmentation efficiency. Besides, there is no public large-scale dataset focused on PA segmentation, which makes it highly challenging to compare the different methods. To benchmark multi-level PA segmentation algorithms, we organized the first \textbf{P}ulmonary \textbf{AR}tery \textbf{SE}gmentation (PARSE) challenge. On the one hand, we focus on both the main PA and the branch PA segmentation. On the other hand, for better clinical application, we assign the same score weight to segmentation efficiency (mainly running time and GPU memory consumption during inference) while ensuring PA segmentation accuracy. We present a summary of the top algorithms and offer some suggestions for efficient and accurate multi-level PA automatic segmentation. We provide the PARSE challenge as open-access for the community to benchmark future algorithm developments at \url{https://parse2022.grand-challenge.org/Parse2022/}.

arXiv:2304.02497공식 코드 · Papers with Code

Hyper-parameter Tuning for Adversarially Robust Models

This work focuses on the problem of hyper-parameter tuning (HPT) for robust (i.e., adversarially trained) models, shedding light on the new challenges and opportunities arising during the HPT process for robust models. To this end, we conduct an extensive experimental study based on 3 popular deep models, in which we explore exhaustively 9 (discretized) HPs, 2 fidelity dimensions, and 2 attack bounds, for a total of 19208 configurations (corresponding to 50 thousand GPU hours). Through this study, we show that the complexity of the HPT problem is further exacerbated in adversarial settings due to the need to independently tune the HPs used during standard and adversarial training: succeeding in doing so (i.e., adopting different HP settings in both phases) can lead to a reduction of up to 80% and 43% of the error for clean and adversarial inputs, respectively. On the other hand, we also identify new opportunities to reduce the cost of HPT for robust models. Specifically, we propose to leverage cheap adversarial training methods to obtain inexpensive, yet highly correlated, estimations of the quality achievable using state-of-the-art methods. We show that, by exploiting this novel idea in conjunction with a recent multi-fidelity optimizer (taKG), the efficiency of the HPT process can be enhanced by up to 2.1x.

arXiv:2304.01951공식 코드 · Papers with Code

TransPimLib: A Library for Efficient Transcendental Functions on Processing-in-Memory Systems

Processing-in-memory (PIM) promises to alleviate the data movement bottleneck in modern computing systems. However, current real-world PIM systems have the inherent disadvantage that their hardware is more constrained than in conventional processors (CPU, GPU), due to the difficulty and cost of building processing elements near or inside the memory. As a result, general-purpose PIM architectures support fairly limited instruction sets and struggle to execute complex operations such as transcendental functions and other hard-to-calculate operations (e.g., square root). These operations are particularly important for some modern workloads, e.g., activation functions in machine learning applications. In order to provide support for transcendental (and other hard-to-calculate) functions in general-purpose PIM systems, we present \emph{TransPimLib}, a library that provides CORDIC-based and LUT-based methods for trigonometric functions, hyperbolic functions, exponentiation, logarithm, square root, etc. We develop an implementation of TransPimLib for the UPMEM PIM architecture and perform a thorough evaluation of TransPimLib's methods in terms of performance and accuracy, using microbenchmarks and three full workloads (Blackscholes, Sigmoid, Softmax). We open-source all our code and datasets at~\url{https://github.com/CMU-SAFARI/transpimlib}.

arXiv:2304.01285공식 코드 · Papers with Code

X-TIME: An in-memory engine for accelerating machine learning on tabular data with CAMs

Structured, or tabular, data is the most common format in data science. While deep learning models have proven formidable in learning from unstructured data such as images or speech, they are less accurate than simpler approaches when learning from tabular data. In contrast, modern tree-based Machine Learning (ML) models shine in extracting relevant information from structured data. An essential requirement in data science is to reduce model inference latency in cases where, for example, models are used in a closed loop with simulation to accelerate scientific discovery. However, the hardware acceleration community has mostly focused on deep neural networks and largely ignored other forms of machine learning. Previous work has described the use of an analog content addressable memory (CAM) component for efficiently mapping random forests. In this work, we focus on an overall analog-digital architecture implementing a novel increased precision analog CAM and a programmable network on chip allowing the inference of state-of-the-art tree-based ML models, such as XGBoost and CatBoost. Results evaluated in a single chip at 16nm technology show 119x lower latency at 9740x higher throughput compared with a state-of-the-art GPU, with a 19W peak power consumption.