PyTorchKR Papers

최신 논문

총 2,153편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2305.19045

Back to Patterns: Efficient Japanese Morphological Analysis with Feature-Sequence Trie

Accurate neural models are much less efficient than non-neural models and are useless for processing billions of social media posts or handling user queries in real time with a limited budget. This study revisits the fastest pattern-based NLP methods to make them as accurate as possible, thus yielding a strikingly simple yet surprisingly accurate morphological analyzer for Japanese. The proposed method induces reliable patterns from a morphological dictionary and annotated data. Experimental results on two standard datasets confirm that the method exhibits comparable accuracy to learning-based baselines, while boasting a remarkable throughput of over 1,000,000 sentences per second on a single modern CPU. The source code is available at https://www.tkl.iis.u-tokyo.ac.jp/~ynaga/jagger/

arXiv:2305.18932공식 코드 · Papers with Code

The Information Retrieval Experiment Platform

We integrate ir_datasets, ir_measures, and PyTerrier with TIRA in the Information Retrieval Experiment Platform (TIREx) to promote more standardized, reproducible, scalable, and even blinded retrieval experiments. Standardization is achieved when a retrieval approach implements PyTerrier's interfaces and the input and output of an experiment are compatible with ir_datasets and ir_measures. However, none of this is a must for reproducibility and scalability, as TIRA can run any dockerized software locally or remotely in a cloud-native execution environment. Version control and caching ensure efficient (re)execution. TIRA allows for blind evaluation when an experiment runs on a remote server or cloud not under the control of the experimenter. The test data and ground truth are then hidden from public access, and the retrieval software has to process them in a sandbox that prevents data leaks. We currently host an instance of TIREx with 15 corpora (1.9 billion documents) on which 32 shared retrieval tasks are based. Using Docker images of 50 standard retrieval approaches, we automatically evaluated all approaches on all tasks (50 $\cdot$ 32 = 1,600~runs) in less than a week on a midsize cluster (1,620 CPU cores and 24 GPUs). This instance of TIREx is open for submissions and will be integrated with the IR Anthology, as well as released open source.

arXiv:2305.18691공식 코드 · Papers with Code

Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts

Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention in ViT and the need to activate an entire large MTL model for one task. M$^3$ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE), where only a small portion of subnetworks ("experts") are sparsely and dynamically activated based on the current task. M$^3$ViT achieves better accuracy and over 80% computation reduction but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations, including (1) a novel reordering mechanism for self-attention, which requires only constant bandwidth regardless of the target parallelism; (2) a fast single-pass softmax approximation; (3) an accurate and low-cost GELU approximation; (4) a unified and flexible computing unit that is shared by almost all computational layers to maximally reduce resource usage; and (5) uniquely for M$^3$ViT, a novel patch reordering method to eliminate memory access overhead. Edge-MoE achieves 2.24x and 4.90x better energy efficiency comparing with GPU and CPU, respectively. A real-time video demonstration is available online, along with our open-source code written using High-Level Synthesis.

arXiv:2305.18575공식 코드 · Papers with Code

Search-Based Regular Expression Inference on a GPU

Regular expression inference (REI) is a supervised machine learning and program synthesis problem that takes a cost metric for regular expressions, and positive and negative examples of strings as input. It outputs a regular expression that is precise (i.e., accepts all positive and rejects all negative examples), and minimal w.r.t. to the cost metric. We present a novel algorithm for REI over arbitrary alphabets that is enumerative and trades off time for space. Our main algorithmic idea is to implement the search space of regular expressions succinctly as a contiguous matrix of bitvectors. Collectively, the bitvectors represent, as characteristic sequences, all sub-languages of the infix-closure of the union of positive and negative examples. Mathematically, this is a semiring of (a variant of) formal power series. Infix-closure enables bottom-up compositional construction of larger from smaller regular expressions using the operations of our semiring. This minimises data movement and data-dependent branching, hence maximises data-parallelism. In addition, the infix-closure remains unchanged during the search, hence search can be staged: first pre-compute various expensive operations, and then run the compute intensive search process. We provide two C++ implementations, one for general purpose CPUs and one for Nvidia GPUs (using CUDA). We benchmark both on Google Colab Pro: the GPU implementation is on average over 1000x faster than the CPU implementation on the hardest benchmarks.

arXiv:2305.17144공식 코드 · Papers with Code

Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

The captivating realm of Minecraft has attracted substantial research interest in recent years, serving as a rich platform for developing intelligent agents capable of functioning in open-world environments. However, the current research landscape predominantly focuses on specific objectives, such as the popular "ObtainDiamond" task, and has not yet shown effective generalization to a broader spectrum of tasks. Furthermore, the current leading success rate for the "ObtainDiamond" task stands at around 20%, highlighting the limitations of Reinforcement Learning (RL) based controllers used in existing methods. To tackle these challenges, we introduce Ghost in the Minecraft (GITM), a novel framework integrates Large Language Models (LLMs) with text-based knowledge and memory, aiming to create Generally Capable Agents (GCAs) in Minecraft. These agents, equipped with the logic and common sense capabilities of LLMs, can skillfully navigate complex, sparse-reward environments with text-based interactions. We develop a set of structured actions and leverage LLMs to generate action plans for the agents to execute. The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate on the "ObtainDiamond" task, demonstrating superior robustness compared to traditional RL-based controllers. Notably, our agent is the first to procure all items in the Minecraft Overworld technology tree, demonstrating its extensive capabilities. GITM does not need any GPU for training, but a single CPU node with 32 CPU cores is enough. This research shows the potential of LLMs in developing capable agents for handling long-horizon, complex tasks and adapting to uncertainties in open-world environments. See the project website at https://github.com/OpenGVLab/GITM.

arXiv:2305.18205공식 코드 · Papers with Code

Pulse shape discrimination based on the Tempotron: a powerful classifier on GPU

This study utilized the Tempotron, a robust classifier based on a third-generation neural network model, for pulse shape discrimination. By eliminating the need for manual feature extraction, the Tempotron model can process pulse signals directly, generating discrimination results based on prior knowledge. The study performed experiments using GPU acceleration, resulting in over 500 times faster compared to the CPU-based model, and investigated the impact of noise augmentation on the Tempotron performance. Experimental results substantiated that Tempotron serves as a formidable classifier, adept at accomplishing high discrimination accuracy on both AmBe and time-of-flight PuBe datasets. Furthermore, analyzing the neural activity of Tempotron during training shed light on its learning characteristics and aided in selecting its hyperparameters. Moreover, the study addressed the constraints and potential avenues for future development in utilizing the Tempotron for pulse shape discrimination. The dataset used in this study and the GPU-based Tempotron are publicly available on GitHub at https://github.com/HaoranLiu507/TempotronGPU.

arXiv:2305.16608공식 코드 · Papers with Code

AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec

A good audio codec for live applications such as telecommunication is characterized by three key properties: (1) compression, i.e.\ the bitrate that is required to transmit the signal should be as low as possible; (2) latency, i.e.\ encoding and decoding the signal needs to be fast enough to enable communication without or with only minimal noticeable delay; and (3) reconstruction quality of the signal. In this work, we propose an open-source, streamable, and real-time neural audio codec that achieves strong performance along all three axes: it can reconstruct highly natural sounding 48~kHz speech signals while operating at only 12~kbps and running with less than 6~ms (GPU)/10~ms (CPU) latency. An efficient training paradigm is also demonstrated for developing such neural audio codecs for real-world scenarios. Both objective and subjective evaluations using the VCTK corpus are provided. To sum up, AudioDec is a well-developed plug-and-play benchmark for audio codec applications.

arXiv:2305.16513

Sliding Window Sum Algorithms for Deep Neural Networks

Sliding window sums are widely used for string indexing, hashing and time series analysis. We have developed a family of the generic vectorized sliding sum algorithms that provide speedup of O(P/w) for window size $w$ and number of processors P. For a sum with a commutative operator the speedup is improved to O(P/log(w)). Even more important, our algorithms exhibit efficient memory access patterns. In this paper we study the application of the sliding sum algorithms to the training and inference of the Deep Neural Networks. We demonstrate how both pooling and convolution primitives could be expressed as sliding sums and evaluated by the compute kernels with the shared structure. We show that the sliding sum convolution kernels are more efficient than the commonly used GEMM kernels on the CPU, and could even outperform their GPU counterparts.

arXiv:2305.15422

Facial Expression Recognition at the Edge: CPU vs GPU vs VPU vs TPU

Facial Expression Recognition (FER) plays an important role in human-computer interactions and is used in a wide range of applications. Convolutional Neural Networks (CNN) have shown promise in their ability to classify human facial expressions, however, large CNNs are not well-suited to be implemented on resource- and energy-constrained IoT devices. In this work, we present a hierarchical framework for developing and optimizing hardware-aware CNNs tuned for deployment at the edge. We perform a comprehensive analysis across various edge AI accelerators including NVIDIA Jetson Nano, Intel Neural Compute Stick, and Coral TPU. Using the proposed strategy, we achieved a peak accuracy of 99.49% when testing on the CK+ facial expression recognition dataset. Additionally, we achieved a minimum inference latency of 0.39 milliseconds and a minimum power consumption of 0.52 Watts.

arXiv:2305.13970

Darwin: A DRAM-based Multi-level Processing-in-Memory Architecture for Data Analytics

Processing-in-memory (PIM) architecture is an inherent match for data analytics application, but we observe major challenges to address when accelerating it using PIM. In this paper, we propose Darwin, a practical LRDIMM-based multi-level PIM architecture for data analytics, which fully exploits the internal bandwidth of DRAM using the bank-, bank group-, chip-, and rank-level parallelisms. Considering the properties of data analytics operators and DRAM's area constraints, Darwin maximizes the internal data bandwidth by placing the PIM processing units, buffers, and control circuits across the hierarchy of DRAM. More specifically, it introduces the bank processing unit for each bank in which a single instruction multiple data (SIMD) unit handles regular data analytics operators and bank group processing unit for each bank group to handle workload imbalance in the condition-oriented data analytics operators. Furthermore, Darwin supports a novel PIM instruction architecture that concatenates instructions for multiple thread executions on bank group processing entities, addressing the command bottleneck by enabling separate control of up to 512 different in-memory processing units simultaneously. We build a cycle-accurate simulation framework to evaluate Darwin with various DRAM configurations, optimization schemes and workloads. Darwin achieves up to 14.7x speedup over the non-optimized version. Finally, the proposed Darwin architecture achieves 4.0x-43.9x higher throughput and reduces energy consumption by 85.7% than the baseline CPU system (Intel Xeon Gold 6226 + 4 channels of DDR4-2933). Compared to the state-of-the-art PIM, Darwin achieves up to 7.5x and 7.1x in the basic query operators and TPC-H queries, respectively. Darwin is based on the latest GDDR6 and requires only 5.6% area overhead, suggesting a promising PIM solution for the future main memory system.

arXiv:2305.13905공식 코드 · Papers with Code

EfficientSpeech: An On-Device Text to Speech Model

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on speech quality with cloud inference in mind. Neural TTS models are generally not designed to perform standalone speech syntheses on resource-constrained and no Internet access edge devices. In this work, an efficient neural TTS called EfficientSpeech that synthesizes speech on an ARM CPU in real-time is proposed. EfficientSpeech uses a shallow non-autoregressive pyramid-structure transformer forming a U-Network. EfficientSpeech has 266k parameters and consumes 90 MFLOPS only or about 1% of the size and amount of computation in modern compact models such as Mixer-TTS. EfficientSpeech achieves an average mel generation real-time factor of 104.3 on an RPi4. Human evaluation shows only a slight degradation in audio quality as compared to FastSpeech2.

arXiv:2305.12266

LightESD: Fully-Automated and Lightweight Anomaly Detection Framework for Edge Computing

Anomaly detection is widely used in a broad range of domains from cybersecurity to manufacturing, finance, and so on. Deep learning based anomaly detection has recently drawn much attention because of its superior capability of recognizing complex data patterns and identifying outliers accurately. However, deep learning models are typically iteratively optimized in a central server with input data gathered from edge devices, and such data transfer between edge devices and the central server impose substantial overhead on the network and incur additional latency and energy consumption. To overcome this problem, we propose a fully-automated, lightweight, statistical learning based anomaly detection framework called LightESD. It is an on-device learning method without the need for data transfer between edge and server, and is extremely lightweight that most low-end edge devices can easily afford with negligible delay, CPU/memory utilization, and power consumption. Yet, it achieves highly competitive detection accuracy. Another salient feature is that it can auto-adapt to probably any dataset without manually setting or configuring model parameters or hyperparameters, which is a drawback of most existing methods. We focus on time series data due to its pervasiveness in edge applications such as IoT. Our evaluation demonstrates that LightESD outperforms other SOTA methods on detection accuracy, efficiency, and resource consumption. Additionally, its fully automated feature gives it another competitive advantage in terms of practical usability and generalizability.

arXiv:2305.12213

Taming Resource Heterogeneity In Distributed ML Training With Dynamic Batching

Current techniques and systems for distributed model training mostly assume that clusters are comprised of homogeneous servers with a constant resource availability. However, cluster heterogeneity is pervasive in computing infrastructure, and is a fundamental characteristic of low-cost transient resources (such as EC2 spot instances). In this paper, we develop a dynamic batching technique for distributed data-parallel training that adjusts the mini-batch sizes on each worker based on its resource availability and throughput. Our mini-batch controller seeks to equalize iteration times on all workers, and facilitates training on clusters comprised of servers with different amounts of CPU and GPU resources. This variable mini-batch technique uses proportional control and ideas from PID controllers to find stable mini-batch sizes. Our empirical evaluation shows that dynamic batching can reduce model training times by more than 4x on heterogeneous clusters.

arXiv:2305.10931

Lyapunov-Driven Deep Reinforcement Learning for Edge Inference Empowered by Reconfigurable Intelligent Surfaces

In this paper, we propose a novel algorithm for energy-efficient, low-latency, accurate inference at the wireless edge, in the context of 6G networks endowed with reconfigurable intelligent surfaces (RISs). We consider a scenario where new data are continuously generated/collected by a set of devices and are handled through a dynamic queueing system. Building on the marriage between Lyapunov stochastic optimization and deep reinforcement learning (DRL), we devise a dynamic learning algorithm that jointly optimizes the data compression scheme, the allocation of radio resources (i.e., power, transmission precoding), the computation resources (i.e., CPU cycles), and the RIS reflectivity parameters (i.e., phase shifts), with the aim of performing energy-efficient edge classification with end-to-end (E2E) delay and inference accuracy constraints. The proposed strategy enables dynamic control of the system and of the wireless propagation environment, performing a low-complexity optimization on a per-slot basis while dealing with time-varying radio channels and task arrivals, whose statistics are unknown. Numerical results assess the performance of the proposed RIS-empowered edge inference strategy in terms of trade-off between energy, delay, and accuracy of a classification task.

arXiv:2305.11101

XFormer: Fast and Accurate Monocular 3D Body Capture

We present XFormer, a novel human mesh and motion capture method that achieves real-time performance on consumer CPUs given only monocular images as input. The proposed network architecture contains two branches: a keypoint branch that estimates 3D human mesh vertices given 2D keypoints, and an image branch that makes predictions directly from the RGB image features. At the core of our method is a cross-modal transformer block that allows information to flow across these two branches by modeling the attention between 2D keypoint coordinates and image spatial features. Our architecture is smartly designed, which enables us to train on various types of datasets including images with 2D/3D annotations, images with 3D pseudo labels, and motion capture datasets that do not have associated images. This effectively improves the accuracy and generalization ability of our system. Built on a lightweight backbone (MobileNetV3), our method runs blazing fast (over 30fps on a single CPU core) and still yields competitive accuracy. Furthermore, with an HRNet backbone, XFormer delivers state-of-the-art performance on Huamn3.6 and 3DPW datasets.

arXiv:2305.10863공식 코드 · Papers with Code

Quiver: Supporting GPUs for Low-Latency, High-Throughput GNN Serving with Workload Awareness

Systems for serving inference requests on graph neural networks (GNN) must combine low latency with high throughout, but they face irregular computation due to skew in the number of sampled graph nodes and aggregated GNN features. This makes it challenging to exploit GPUs effectively: using GPUs to sample only a few graph nodes yields lower performance than CPU-based sampling; and aggregating many features exhibits high data movement costs between GPUs and CPUs. Therefore, current GNN serving systems use CPUs for graph sampling and feature aggregation, limiting throughput. We describe Quiver, a distributed GPU-based GNN serving system with low-latency and high-throughput. Quiver's key idea is to exploit workload metrics for predicting the irregular computation of GNN requests, and governing the use of GPUs for graph sampling and feature aggregation: (1) for graph sampling, Quiver calculates the probabilistic sampled graph size, a metric that predicts the degree of parallelism in graph sampling. Quiver uses this metric to assign sampling tasks to GPUs only when the performance gains surpass CPU-based sampling; and (2) for feature aggregation, Quiver relies on the feature access probability to decide which features to partition and replicate across a distributed GPU NUMA topology. We show that Quiver achieves up to 35 times lower latency with an 8 times higher throughput compared to state-of-the-art GNN approaches (DGL and PyG).

arXiv:2305.08227공식 코드 · Papers with Code

DeepFilterNet: Perceptually Motivated Real-Time Speech Enhancement

Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep Filtering (DF) was proposed to directly estimate a complex filter in frequency domain to take advantage of these correlations. In this work, we present a real-time speech enhancement demo using DeepFilterNet. DeepFilterNet's efficiency is enabled by exploiting domain knowledge of speech production and psychoacoustic perception. Our model is able to match state-of-the-art speech enhancement benchmarks while achieving a real-time-factor of 0.19 on a single threaded notebook CPU. The framework as well as pretrained weights have been published under an open source license.

arXiv:2305.07778

Accelerator-Aware Training for Transducer-Based Speech Recognition

Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network accelerator (NNA) chips, which leverage highly parallelized fixed-point arithmetic to improve runtime memory and latency. In this work, we replicate the NNA operators during the training phase, accounting for the degradation due to low-precision inference on the NNA in back-propagation. Our proposed method efficiently emulates NNA operations, thus foregoing the need to transfer quantization error-prone data to the Central Processing Unit (CPU), ultimately reducing the user perceived latency (UPL). We apply our approach to Recurrent Neural Network-Transducer (RNN-T), an attractive architecture for on-device streaming speech recognition tasks. We train and evaluate models on 270K hours of English data and show a 5-7% improvement in engine latency while saving up to 10% relative degradation in WER.

arXiv:2305.08750공식 코드 · Papers with Code

Fast and Attributed Change Detection on Dynamic Graphs with Density of States

How can we detect traffic disturbances from international flight transportation logs or changes to collaboration dynamics in academic networks? These problems can be formulated as detecting anomalous change points in a dynamic graph. Current solutions do not scale well to large real-world graphs, lack robustness to large amounts of node additions/deletions, and overlook changes in node attributes. To address these limitations, we propose a novel spectral method: Scalable Change Point Detection (SCPD). SCPD generates an embedding for each graph snapshot by efficiently approximating the distribution of the Laplacian spectrum at each step. SCPD can also capture shifts in node attributes by tracking correlations between attributes and eigenvectors. Through extensive experiments using synthetic and real-world data, we show that SCPD (a) achieves state-of-the art performance, (b) is significantly faster than the state-of-the-art methods and can easily process millions of edges in a few CPU minutes, (c) can effectively tackle a large quantity of node attributes, additions or deletions and (d) discovers interesting events in large real-world graphs. The code is publicly available at https://github.com/shenyangHuang/SCPD.git

arXiv:2305.07027공식 코드 · Papers with Code

EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention

Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them unsuitable for real-time applications. In this paper, we propose a family of high-speed vision transformers named EfficientViT. We find that the speed of existing transformer models is commonly bounded by memory inefficient operations, especially the tensor reshaping and element-wise functions in MHSA. Therefore, we design a new building block with a sandwich layout, i.e., using a single memory-bound MHSA between efficient FFN layers, which improves memory efficiency while enhancing channel communication. Moreover, we discover that the attention maps share high similarities across heads, leading to computational redundancy. To address this, we present a cascaded group attention module feeding attention heads with different splits of the full feature, which not only saves computation cost but also improves attention diversity. Comprehensive experiments demonstrate EfficientViT outperforms existing efficient models, striking a good trade-off between speed and accuracy. For instance, our EfficientViT-M5 surpasses MobileNetV3-Large by 1.9% in accuracy, while getting 40.4% and 45.2% higher throughput on Nvidia V100 GPU and Intel Xeon CPU, respectively. Compared to the recent efficient model MobileViT-XXS, EfficientViT-M2 achieves 1.8% superior accuracy, while running 5.8x/3.7x faster on the GPU/CPU, and 7.4x faster when converted to ONNX format. Code and models are available at https://github.com/microsoft/Cream/tree/main/EfficientViT.