PyTorchKR Papers

최신 논문

총 5,357편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2310.11862

Learning to Generate Parameters of ConvNets for Unseen Image Data

Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn network parameters, which makes training very time- and resource-intensive. In this paper, we propose a new training paradigm and formulate the parameter learning of ConvNets into a prediction task: given a ConvNet architecture, we observe there exist correlations between image datasets and their corresponding optimal network parameters, and explore if we can learn a hyper-mapping between them to capture the relations, such that we can directly predict the parameters of the network for an image dataset never seen during the training phase. To do this, we put forward a new hypernetwork based model, called PudNet, which intends to learn a mapping between datasets and their corresponding network parameters, and then predicts parameters for unseen data with only a single forward propagation. Moreover, our model benefits from a series of adaptive hyper recurrent units sharing weights to capture the dependencies of parameters among different network layers. Extensive experiments demonstrate that our proposed method achieves good efficacy for unseen image datasets on two kinds of settings: Intra-dataset prediction and Inter-dataset prediction. Our PudNet can also well scale up to large-scale datasets, e.g., ImageNet-1K. It takes 8967 GPU seconds to train ResNet-18 on the ImageNet-1K using GC from scratch and obtain a top-5 accuracy of 44.65%. However, our PudNet costs only 3.89 GPU seconds to predict the network parameters of ResNet-18 achieving comparable performance (44.92%), more than 2,300 times faster than the traditional training paradigm.

arXiv:2310.11374공식 코드 · Papers with Code

DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversations

Large language models (LLMs) and their variants have shown extraordinary efficacy across numerous downstream natural language processing (NLP) tasks, which has presented a new vision for the development of NLP. Despite their remarkable performance in natural language generating (NLG), LLMs lack a distinct focus on the emotion understanding domain. As a result, using LLMs for emotion recognition may lead to suboptimal and inadequate precision. Another limitation of LLMs is that they are typical trained without leveraging multi-modal information. To overcome these limitations, we propose DialogueLLM, a context and emotion knowledge tuned LLM that is obtained by fine-tuning LLaMA models with 13,638 multi-modal (i.e., texts and videos) emotional dialogues. The visual information is considered as the supplementary knowledge to construct high-quality instructions. We offer a comprehensive evaluation of our proposed model on three benchmarking emotion recognition in conversations (ERC) datasets and compare the results against the SOTA baselines and other SOTA LLMs. Additionally, DialogueLLM-7B can be easily trained using LoRA on a 40GB A100 GPU in 5 hours, facilitating reproducibility for other researchers.

arXiv:2310.11448

4K4D: Real-Time 4D View Synthesis at 4K Resolution

This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution. Recently, some methods on dynamic view synthesis have shown impressive rendering quality. However, their speed is still limited when rendering high-resolution images. To overcome this problem, we propose 4K4D, a 4D point cloud representation that supports hardware rasterization and enables unprecedented rendering speed. Our representation is built on a 4D feature grid so that the points are naturally regularized and can be robustly optimized. In addition, we design a novel hybrid appearance model that significantly boosts the rendering quality while preserving efficiency. Moreover, we develop a differentiable depth peeling algorithm to effectively learn the proposed model from RGB videos. Experiments show that our representation can be rendered at over 400 FPS on the DNA-Rendering dataset at 1080p resolution and 80 FPS on the ENeRF-Outdoor dataset at 4K resolution using an RTX 4090 GPU, which is 30x faster than previous methods and achieves the state-of-the-art rendering quality. Our project page is available at https://zju3dv.github.io/4k4d/.

arXiv:2310.11131

FROST: Towards Energy-efficient AI-on-5G Platforms -- A GPU Power Capping Evaluation

The Open Radio Access Network (O-RAN) is a burgeoning market with projected growth in the upcoming years. RAN has the highest CAPEX impact on the network and, most importantly, consumes 73% of its total energy. That makes it an ideal target for optimisation through the integration of Machine Learning (ML). However, the energy consumption of ML is frequently overlooked in such ecosystems. Our work addresses this critical aspect by presenting FROST - Flexible Reconfiguration method with Online System Tuning - a solution for energy-aware ML pipelines that adhere to O-RAN's specifications and principles. FROST is capable of profiling the energy consumption of an ML pipeline and optimising the hardware accordingly, thereby limiting the power draw. Our findings indicate that FROST can achieve energy savings of up to 26.4% without compromising the model's accuracy or introducing significant time delays.

arXiv:2310.10769공식 코드 · Papers with Code

LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation

With the impressive progress in diffusion-based text-to-image generation, extending such powerful generative ability to text-to-video raises enormous attention. Existing methods either require large-scale text-video pairs and a large number of training resources or learn motions that are precisely aligned with template videos. It is non-trivial to balance a trade-off between the degree of generation freedom and the resource costs for video generation. In our study, we present a few-shot-based tuning framework, LAMP, which enables text-to-image diffusion model Learn A specific Motion Pattern with 8~16 videos on a single GPU. Specifically, we design a first-frame-conditioned pipeline that uses an off-the-shelf text-to-image model for content generation so that our tuned video diffusion model mainly focuses on motion learning. The well-developed text-to-image techniques can provide visually pleasing and diverse content as generation conditions, which highly improves video quality and generation freedom. To capture the features of temporal dimension, we expand the pretrained 2D convolution layers of the T2I model to our novel temporal-spatial motion learning layers and modify the attention blocks to the temporal level. Additionally, we develop an effective inference trick, shared-noise sampling, which can improve the stability of videos with computational costs. Our method can also be flexibly applied to other tasks, e.g. real-world image animation and video editing. Extensive experiments demonstrate that LAMP can effectively learn the motion pattern on limited data and generate high-quality videos. The code and models are available at https://rq-wu.github.io/projects/LAMP.

arXiv:2310.11316공식 코드 · Papers with Code

MonoSKD: General Distillation Framework for Monocular 3D Object Detection via Spearman Correlation Coefficient

Monocular 3D object detection is an inherently ill-posed problem, as it is challenging to predict accurate 3D localization from a single image. Existing monocular 3D detection knowledge distillation methods usually project the LiDAR onto the image plane and train the teacher network accordingly. Transferring LiDAR-based model knowledge to RGB-based models is more complex, so a general distillation strategy is needed. To alleviate cross-modal prob-lem, we propose MonoSKD, a novel Knowledge Distillation framework for Monocular 3D detection based on Spearman correlation coefficient, to learn the relative correlation between cross-modal features. Considering the large gap between these features, strict alignment of features may mislead the training, so we propose a looser Spearman loss. Furthermore, by selecting appropriate distillation locations and removing redundant modules, our scheme saves more GPU resources and trains faster than existing methods. Extensive experiments are performed to verify the effectiveness of our framework on the challenging KITTI 3D object detection benchmark. Our method achieves state-of-the-art performance until submission with no additional inference computational cost. Our codes are available at https://github.com/Senwang98/MonoSKD

arXiv:2310.09912

Unsupervised Discovery of Interpretable Directions in h-space of Pre-trained Diffusion Models

We propose the first unsupervised and learning-based method to identify interpretable directions in h-space of pre-trained diffusion models. Our method is derived from an existing technique that operates on the GAN latent space. Specifically, we employ a shift control module that works on h-space of pre-trained diffusion models to manipulate a sample into a shifted version of itself, followed by a reconstructor to reproduce both the type and the strength of the manipulation. By jointly optimizing them, the model will spontaneously discover disentangled and interpretable directions. To prevent the discovery of meaningless and destructive directions, we employ a discriminator to maintain the fidelity of shifted sample. Due to the iterative generative process of diffusion models, our training requires a substantial amount of GPU VRAM to store numerous intermediate tensors for back-propagating gradient. To address this issue, we propose a general VRAM-efficient training algorithm based on gradient checkpointing technique to back-propagate any gradient through the whole generative process, with acceptable occupancy of VRAM and sacrifice of training efficiency. Compared with existing related works on diffusion models, our method inherently identifies global and scalable directions, without necessitating any other complicated procedures. Extensive experiments on various datasets demonstrate the effectiveness of our method.

arXiv:2310.09554

Neural network scoring for efficient computing

Much work has been dedicated to estimating and optimizing workloads in high-performance computing (HPC) and deep learning. However, researchers have typically relied on few metrics to assess the efficiency of those techniques. Most notably, the accuracy, the loss of the prediction, and the computational time with regard to GPUs or/and CPUs characteristics. It is rare to see figures for power consumption, partly due to the difficulty of obtaining accurate power readings. In this paper, we introduce a composite score that aims to characterize the trade-off between accuracy and power consumption measured during the inference of neural networks. For this purpose, we present a new open-source tool allowing researchers to consider more metrics: granular power consumption, but also RAM/CPU/GPU utilization, as well as storage, and network input/output (I/O). To our best knowledge, it is the first fit test for neural architectures on hardware architectures. This is made possible thanks to reproducible power efficiency measurements. We applied this procedure to state-of-the-art neural network architectures on miscellaneous hardware. One of the main applications and novelties is the measurement of algorithmic power efficiency. The objective is to allow researchers to grasp their algorithms' efficiencies better. This methodology was developed to explore trade-offs between energy usage and accuracy in neural networks. It is also useful when fitting hardware for a specific task or to compare two architectures more accurately, with architecture exploration in mind.

arXiv:2310.09806

Can LSH (Locality-Sensitive Hashing) Be Replaced by Neural Network?

With the rapid development of GPU (Graphics Processing Unit) technologies and neural networks, we can explore more appropriate data structures and algorithms. Recent progress shows that neural networks can partly replace traditional data structures. In this paper, we proposed a novel DNN (Deep Neural Network)-based learned locality-sensitive hashing, called LLSH, to efficiently and flexibly map high-dimensional data to low-dimensional space. LLSH replaces the traditional LSH (Locality-sensitive Hashing) function families with parallel multi-layer neural networks, which reduces the time and memory consumption and guarantees query accuracy simultaneously. The proposed LLSH demonstrate the feasibility of replacing the hash index with learning-based neural networks and open a new door for developers to design and configure data organization more accurately to improve information-searching performance. Extensive experiments on different types of datasets show the superiority of the proposed method in query accuracy, time consumption, and memory usage.

arXiv:2310.09443공식 코드 · Papers with Code

G10: Enabling An Efficient Unified GPU Memory and Storage Architecture with Smart Tensor Migrations

To break the GPU memory wall for scaling deep learning workloads, a variety of architecture and system techniques have been proposed recently. Their typical approaches include memory extension with flash memory and direct storage access. However, these techniques still suffer from suboptimal performance and introduce complexity to the GPU memory management, making them hard to meet the scalability requirement of deep learning workloads today. In this paper, we present a unified GPU memory and storage architecture named G10 driven by the fact that the tensor behaviors of deep learning workloads are highly predictable. G10 integrates the host memory, GPU memory, and flash memory into a unified memory space, to scale the GPU memory capacity while enabling transparent data migrations. Based on this unified GPU memory and storage architecture, G10 utilizes compiler techniques to characterize the tensor behaviors in deep learning workloads. Therefore, it can schedule data migrations in advance by considering the available bandwidth of flash memory and host memory. The cooperative mechanism between deep learning compilers and the unified memory architecture enables G10 to hide data transfer overheads in a transparent manner. We implement G10 based on an open-source GPU simulator. Our experiments demonstrate that G10 outperforms state-of-the-art GPU memory solutions by up to 1.75$\times$, without code modifications to deep learning workloads. With the smart data migration mechanism, G10 can reach 90.3\% of the performance of the ideal case assuming unlimited GPU memory.

arXiv:2310.10505공식 코드 · Papers with Code

ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO is a powerful method designed for general reinforcement learning tasks, it is overly sophisticated for LLMs, leading to laborious hyper-parameter tuning and significant computation burdens. To make RLHF efficient, we present ReMax, which leverages 3 properties of RLHF: fast simulation, deterministic transitions, and trajectory-level rewards. These properties are not exploited in PPO, making it less suitable for RLHF. Building on the renowned REINFORCE algorithm, ReMax does not require training an additional value model as in PPO and is further enhanced with a new variance reduction technique. ReMax offers several benefits over PPO: it is simpler to implement, eliminates more than 4 hyper-parameters in PPO, reduces GPU memory usage, and shortens training time. ReMax can save about 46% GPU memory than PPO when training a 7B model and enables training on A800-80GB GPUs without the memory-saving offloading technique needed by PPO. Applying ReMax to a Mistral-7B model resulted in a 94.78% win rate on the AlpacaEval leaderboard and a 7.739 score on MT-bench, setting a new SOTA for open-source 7B models. These results show the effectiveness of ReMax while addressing the limitations of PPO in LLMs.

arXiv:2310.10343공식 코드 · Papers with Code

ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion

Given a single image of a 3D object, this paper proposes a novel method (named ConsistNet) that is able to generate multiple images of the same object, as if seen they are captured from different viewpoints, while the 3D (multi-view) consistencies among those multiple generated images are effectively exploited. Central to our method is a multi-view consistency block which enables information exchange across multiple single-view diffusion processes based on the underlying multi-view geometry principles. ConsistNet is an extension to the standard latent diffusion model, and consists of two sub-modules: (a) a view aggregation module that unprojects multi-view features into global 3D volumes and infer consistency, and (b) a ray aggregation module that samples and aggregate 3D consistent features back to each view to enforce consistency. Our approach departs from previous methods in multi-view image generation, in that it can be easily dropped-in pre-trained LDMs without requiring explicit pixel correspondences or depth prediction. Experiments show that our method effectively learns 3D consistency over a frozen Zero123 backbone and can generate 16 surrounding views of the object within 40 seconds on a single A100 GPU. Our code will be made available on https://github.com/JiayuYANG/ConsistNet

arXiv:2310.10046공식 코드 · Papers with Code

TRANSOM: An Efficient Fault-Tolerant System for Training LLMs

Large language models (LLMs) with hundreds of billions or trillions of parameters, represented by chatGPT, have achieved profound impact on various fields. However, training LLMs with super-large-scale parameters requires large high-performance GPU clusters and long training periods lasting for months. Due to the inevitable hardware and software failures in large-scale clusters, maintaining uninterrupted and long-duration training is extremely challenging. As a result, A substantial amount of training time is devoted to task checkpoint saving and loading, task rescheduling and restart, and task manual anomaly checks, which greatly harms the overall training efficiency. To address these issues, we propose TRANSOM, a novel fault-tolerant LLM training system. In this work, we design three key subsystems: the training pipeline automatic fault tolerance and recovery mechanism named Transom Operator and Launcher (TOL), the training task multi-dimensional metric automatic anomaly detection system named Transom Eagle Eye (TEE), and the training checkpoint asynchronous access automatic fault tolerance and recovery technology named Transom Checkpoint Engine (TCE). Here, TOL manages the lifecycle of training tasks, while TEE is responsible for task monitoring and anomaly reporting. TEE detects training anomalies and reports them to TOL, who automatically enters the fault tolerance strategy to eliminate abnormal nodes and restart the training task. And the asynchronous checkpoint saving and loading functionality provided by TCE greatly shorten the fault tolerance overhead. The experimental results indicate that TRANSOM significantly enhances the efficiency of large-scale LLM training on clusters. Specifically, the pre-training time for GPT3-175B has been reduced by 28%, while checkpoint saving and loading performance have improved by a factor of 20.

arXiv:2310.09949

Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models

A Retrieval-Augmented Language Model (RALM) combines a large language model (LLM) with a vector database to retrieve context-specific knowledge during text generation. This strategy facilitates impressive generation quality even with smaller models, thus reducing computational demands by orders of magnitude. To serve RALMs efficiently and flexibly, we propose Chameleon, a heterogeneous accelerator system integrating both LLM and vector search accelerators in a disaggregated architecture. The heterogeneity ensures efficient serving for both inference and retrieval, while the disaggregation allows independent scaling of LLM and vector search accelerators to fulfill diverse RALM requirements. Our Chameleon prototype implements vector search accelerators on FPGAs and assigns LLM inference to GPUs, with CPUs as cluster coordinators. Evaluated on various RALMs, Chameleon exhibits up to 2.16$\times$ reduction in latency and 3.18x speedup in throughput compared to the hybrid CPU-GPU architecture. The promising results pave the way for adopting heterogeneous accelerators for not only LLM inference but also vector search in future RALM systems.

arXiv:2310.10170공식 코드 · Papers with Code

Leveraging Knowledge Distillation for Efficient Deep Reinforcement Learning in Resource-Constrained Environments

This paper aims to explore the potential of combining Deep Reinforcement Learning (DRL) with Knowledge Distillation (KD) by distilling various DRL algorithms and studying their distillation effects. By doing so, the computational burden of deep models could be reduced while maintaining the performance. The primary objective is to provide a benchmark for evaluating the performance of different DRL algorithms that have been refined using KD techniques. By distilling these algorithms, the goal is to develop efficient and fast DRL models. This research is expected to provide valuable insights that can facilitate further advancements in this promising direction. By exploring the combination of DRL and KD, this work aims to promote the development of models that require fewer GPU resources, learn more quickly, and make faster decisions in complex environments. The results of this research have the capacity to significantly advance the field of DRL and pave the way for the future deployment of resource-efficient, decision-making intelligent systems.

arXiv:2310.09259공식 코드 · Papers with Code

QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models

Large Language Models (LLMs) from the GPT family have become extremely popular, leading to a race towards reducing their inference costs to allow for efficient local computation. Yet, the vast majority of existing work focuses on weight-only quantization, which can reduce runtime costs in the memory-bound one-token-at-a-time generative setting, but does not address them in compute-bound scenarios, such as batched inference or prompt processing. In this paper, we address the general quantization problem, where both weights and activations should be quantized. We show, for the first time, that the majority of inference computations for large generative models such as LLaMA, OPT, and Falcon can be performed with both weights and activations being cast to 4 bits, in a way that leads to practical speedups, while at the same time maintaining good accuracy. We achieve this via a hybrid quantization strategy called QUIK, which compresses most of the weights and activations to 4-bit, while keeping some outlier weights and activations in higher-precision. The key feature of our scheme is that it is designed with computational efficiency in mind: we provide GPU kernels matching the QUIK format with highly-efficient layer-wise runtimes, which lead to practical end-to-end throughput improvements of up to 3.4x relative to FP16 execution. We provide detailed studies for models from the OPT, LLaMA-2 and Falcon families, as well as a first instance of accurate inference using quantization plus 2:4 sparsity. Code is available at: https://github.com/IST-DASLab/QUIK.

arXiv:2310.08826

Revisiting Multi-modal 3D Semantic Segmentation in Real-world Autonomous Driving

LiDAR and camera are two critical sensors for multi-modal 3D semantic segmentation and are supposed to be fused efficiently and robustly to promise safety in various real-world scenarios. However, existing multi-modal methods face two key challenges: 1) difficulty with efficient deployment and real-time execution; and 2) drastic performance degradation under weak calibration between LiDAR and cameras. To address these challenges, we propose CPGNet-LCF, a new multi-modal fusion framework extending the LiDAR-only CPGNet. CPGNet-LCF solves the first challenge by inheriting the easy deployment and real-time capabilities of CPGNet. For the second challenge, we introduce a novel weak calibration knowledge distillation strategy during training to improve the robustness against the weak calibration. CPGNet-LCF achieves state-of-the-art performance on the nuScenes and SemanticKITTI benchmarks. Remarkably, it can be easily deployed to run in 20ms per frame on a single Tesla V100 GPU using TensorRT TF16 mode. Furthermore, we benchmark performance over four weak calibration levels, demonstrating the robustness of our proposed approach.

arXiv:2310.08708

Polynomial Time Cryptanalytic Extraction of Neural Network Models

Billions of dollars and countless GPU hours are currently spent on training Deep Neural Networks (DNNs) for a variety of tasks. Thus, it is essential to determine the difficulty of extracting all the parameters of such neural networks when given access to their black-box implementations. Many versions of this problem have been studied over the last 30 years, and the best current attack on ReLU-based deep neural networks was presented at Crypto 2020 by Carlini, Jagielski, and Mironov. It resembles a differential chosen plaintext attack on a cryptosystem, which has a secret key embedded in its black-box implementation and requires a polynomial number of queries but an exponential amount of time (as a function of the number of neurons). In this paper, we improve this attack by developing several new techniques that enable us to extract with arbitrarily high precision all the real-valued parameters of a ReLU-based DNN using a polynomial number of queries and a polynomial amount of time. We demonstrate its practical efficiency by applying it to a full-sized neural network for classifying the CIFAR10 dataset, which has 3072 inputs, 8 hidden layers with 256 neurons each, and over million neuronal parameters. An attack following the approach by Carlini et al. requires an exhaustive search over 2 to the power 256 possibilities. Our attack replaces this with our new techniques, which require only 30 minutes on a 256-core computer.

arXiv:2310.08585공식 코드 · Papers with Code

Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenes

This paper aims to tackle the challenge of dynamic view synthesis from multi-view videos. The key observation is that while previous grid-based methods offer consistent rendering, they fall short in capturing appearance details of a complex dynamic scene, a domain where multi-view image-based rendering methods demonstrate the opposite properties. To combine the best of two worlds, we introduce Im4D, a hybrid scene representation that consists of a grid-based geometry representation and a multi-view image-based appearance representation. Specifically, the dynamic geometry is encoded as a 4D density function composed of spatiotemporal feature planes and a small MLP network, which globally models the scene structure and facilitates the rendering consistency. We represent the scene appearance by the original multi-view videos and a network that learns to predict the color of a 3D point from image features, instead of memorizing detailed appearance totally with networks, thereby naturally making the learning of networks easier. Our method is evaluated on five dynamic view synthesis datasets including DyNeRF, ZJU-MoCap, NHR, DNA-Rendering and ENeRF-Outdoor datasets. The results show that Im4D exhibits state-of-the-art performance in rendering quality and can be trained efficiently, while realizing real-time rendering with a speed of 79.8 FPS for 512x512 images, on a single RTX 3090 GPU.

arXiv:2310.08529공식 코드 · Papers with Code

GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models

In recent times, the generation of 3D assets from text prompts has shown impressive results. Both 2D and 3D diffusion models can help generate decent 3D objects based on prompts. 3D diffusion models have good 3D consistency, but their quality and generalization are limited as trainable 3D data is expensive and hard to obtain. 2D diffusion models enjoy strong abilities of generalization and fine generation, but 3D consistency is hard to guarantee. This paper attempts to bridge the power from the two types of diffusion models via the recent explicit and efficient 3D Gaussian splatting representation. A fast 3D object generation framework, named as GaussianDreamer, is proposed, where the 3D diffusion model provides priors for initialization and the 2D diffusion model enriches the geometry and appearance. Operations of noisy point growing and color perturbation are introduced to enhance the initialized Gaussians. Our GaussianDreamer can generate a high-quality 3D instance or 3D avatar within 15 minutes on one GPU, much faster than previous methods, while the generated instances can be directly rendered in real time. Demos and code are available at https://taoranyi.com/gaussiandreamer/.