In simulation of nuclear reactor physics using the Monte Carlo neutron transport method on GPUs, the sorting of particles plays a significant role in performance of calculation. Traditionally, CPUs and GPUs are separated devices connected at low data transfer rate and high data transfer latency. Emerging computing chips tend to integrate CPUs and GPUs. One example is the Apple silicon chips with unified memory. Such unified memory chips have opened doors for new strategies of collaboration between CPUs and GPUs for Monte Carlo neutron transport. Sorting particle on CPU and transport on GPU is an example of such new strategy, which has been suffering the high CPU-GPU data transfer latency on the traditional devices with separated CPU and GPU. The finding is that for the Apple M2 max chip, sorting on CPU leads to better performance per power than sorting on GPU for the ExaSMR whole core benchmark problems and the HTR-10 high temperature gas reactor fuel pebble problem. The partially sorted particle order has been identified to contribute to the higher performance with CPU sort than GPU. The in-house code using both CPU and GPU achieves 7.5 times power efficiency that of OpenMC on CPU for ExaSMR whole core benchmark with depleted fuel, and 150 times for HTR-10 fuel pebble benchmark with depleted fuel.
相關內容
The integration of Foundation Models (FMs) with Federated Learning (FL) presents a transformative paradigm in Artificial Intelligence (AI), offering enhanced capabilities while addressing concerns of privacy, data decentralization, and computational efficiency. This paper provides a comprehensive survey of the emerging field of Federated Foundation Models (FedFM), elucidating their synergistic relationship and exploring novel methodologies, challenges, and future directions that the FL research field needs to focus on in order to thrive in the age of foundation models. A systematic multi-tiered taxonomy is proposed, categorizing existing FedFM approaches for model training, aggregation, trustworthiness, and incentivization. Key challenges, including how to enable FL to deal with high complexity of computational demands, privacy considerations, contribution evaluation, and communication efficiency, are thoroughly discussed. Moreover, the paper explores the intricate challenges of communication, scalability and security inherent in training/fine-tuning FMs via FL, highlighting the potential of quantum computing to revolutionize the training, inference, optimization and data encryption processes. This survey underscores the importance of further research to propel innovation in FedFM, emphasizing the need for developing trustworthy solutions. It serves as a foundational guide for researchers and practitioners interested in contributing to this interdisciplinary and rapidly advancing field.
Language Models (LMs) acquire parametric knowledge from their training process, embedding it within their weights. The increasing scalability of LMs, however, poses significant challenges for understanding a model's inner workings and further for updating or correcting this embedded knowledge without the significant cost of retraining. This underscores the importance of unveiling exactly what knowledge is stored and its association with specific model components. Instance Attribution (IA) and Neuron Attribution (NA) offer insights into this training-acquired knowledge, though they have not been compared systematically. Our study introduces a novel evaluation framework to quantify and compare the knowledge revealed by IA and NA. To align the results of the methods we introduce the attribution method NA-Instances to apply NA for retrieving influential training instances, and IA-Neurons to discover important neurons of influential instances discovered by IA. We further propose a comprehensive list of faithfulness tests to evaluate the comprehensiveness and sufficiency of the explanations provided by both methods. Through extensive experiments and analysis, we demonstrate that NA generally reveals more diverse and comprehensive information regarding the LM's parametric knowledge compared to IA. Nevertheless, IA provides unique and valuable insights into the LM's parametric knowledge, which are not revealed by NA. Our findings further suggest the potential of a synergistic approach of combining the diverse findings of IA and NA for a more holistic understanding of an LM's parametric knowledge.
This report introduces a solution to the Topic 1 Zero-shot Image Captioning of 2024 NICE : New frontiers for zero-shot Image Captioning Evaluation. In contrast to NICE 2023 datasets, this challenge involves new annotations by humans with significant differences in caption style and content. Therefore, we enhance image captions effectively through retrieval augmentation and caption grading methods. At the data level, we utilize high-quality captions generated by image caption models as training data to address the gap in text styles. At the model level, we employ OFA (a large-scale visual-language pre-training model based on handcrafted templates) to perform the image captioning task. Subsequently, we propose caption-level strategy for the high-quality caption data generated by the image caption models and integrate them with retrieval augmentation strategy into the template to compel the model to generate higher quality, more matching, and semantically enriched captions based on the retrieval augmentation prompts. Our approach achieves a CIDEr score of 234.11.
In this paper, we tackle the new task of video-based Activated Muscle Group Estimation (AMGE) aiming at identifying active muscle regions during physical activity in the wild. To this intent, we provide the MuscleMap dataset featuring >15K video clips with 135 different activities and 20 labeled muscle groups. This dataset opens the vistas to multiple video-based applications in sports and rehabilitation medicine under flexible environment constraints. The proposed MuscleMap dataset is constructed with YouTube videos, specifically targeting High-Intensity Interval Training (HIIT) physical exercise in the wild. To make the AMGE model applicable in real-life situations, it is crucial to ensure that the model can generalize well to numerous types of physical activities not present during training and involving new combinations of activated muscles. To achieve this, our benchmark also covers an evaluation setting where the model is exposed to activity types excluded from the training set. Our experiments reveal that the generalizability of existing architectures adapted for the AMGE task remains a challenge. Therefore, we also propose a new approach, TransM3E, which employs a multi-modality feature fusion mechanism between both the video transformer model and the skeleton-based graph convolution model with novel cross-modal knowledge distillation executed on multi-classification tokens. The proposed method surpasses all popular video classification models when dealing with both, previously seen and new types of physical activities. The contributed dataset and code will be publicly available at //github.com/KPeng9510/MuscleMap.
Natural Language Processing (NLP) techniques are being used more frequently to improve high-tech Augmentative and Alternative Communication (AAC), but many of these techniques are integrated without the inclusion of the users' perspectives. As many of these tools are created with children in mind, autistic adults are often neglected in the design of AAC tools to begin with. We conducted in-depth interviews with 12 autistic adults to find the pain points of current AAC and determine what general technological advances they would find helpful. We found that in addition to technological issues, there are many societal issues as well. We found 9 different categories of themes from our interviews: input options, output options, selecting or adapting AAC for a good fit, when to start or swap AAC, benefits (of use), access (to AAC), stumbling blocks for continued use, social concerns, and lack of control. In this paper, we go through these nine categories in depth and then suggest possible guidelines for the NLP community, AAC application makers, and policy makers to improve AAC use for autistic adults.
This work addresses the problem of simulating Gaussian random fields that are continuously indexed over a class of metric graphs, termed graphs with Euclidean edges, being more general and flexible than linear networks. We introduce three general algorithms that allow to reconstruct a wide spectrum of random fields having a covariance function that depends on a specific metric, called resistance metric, and proposed in recent literature. The algorithms are applied to a synthetic case study consisting of a street network. They prove to be fast and accurate in that they reproduce the target covariance function and provide random fields whose finite-dimensional distributions are approximately Gaussian.
In Autonomous Driving (AD) transparency and safety are paramount, as mistakes are costly. However, neural networks used in AD systems are generally considered black boxes. As a countermeasure, we have methods of explainable AI (XAI), such as feature relevance estimation and dimensionality reduction. Coarse graining techniques can also help reduce dimensionality and find interpretable global patterns. A specific coarse graining method is Renormalization Groups from statistical physics. It has previously been applied to Restricted Boltzmann Machines (RBMs) to interpret unsupervised learning. We refine this technique by building a transparent backbone model for convolutional variational autoencoders (VAE) that allows mapping latent values to input features and has performance comparable to trained black box VAEs. Moreover, we propose a custom feature map visualization technique to analyze the internal convolutional layers in the VAE to explain internal causes of poor reconstruction that may lead to dangerous traffic scenarios in AD applications. In a second key contribution, we propose explanation and evaluation techniques for the internal dynamics and feature relevance of prediction networks. We test a long short-term memory (LSTM) network in the computer vision domain to evaluate the predictability and in future applications potentially safety of prediction models. We showcase our methods by analyzing a VAE-LSTM world model that predicts pedestrian perception in an urban traffic situation.
We identify potential merits of faster-than-Nyquist (FTN) signaling in the finite blocklength (FBL) regime. A unique aspect of FTN signaling is that it can increase the blocklength by packing more data symbols within the same time and frequency to yield strictly higher number of independent signaling dimensions than that of Nyquist rate signaling. Using the finite-blocklength information theory, we provide tight bounds on the maximum channel coding rate (MCCR) of FTN signaling for any finite time-bandwidth product. The merits are categorized into two operating regions of FTN, i.e., when the time-acceleration factor of FTN, $\tau$, is above or below a certain threshold $\tau_{0}$. When $\tau > \tau_{0}$, FTN has both higher channel capacity and MCCR than that of Nyquist rate signaling, when the utilized pulse shape is non-sinc. Since the issues associated with the ideal sinc pulse only get exacerbated when packets are short, the benefit of FTN becomes more significant in the FBL regime. On the other hand, when $\tau < \tau_{0}$, the channel capacity is fixed but MCCR of FTN can continue to increase to a certain degree, thereby reducing the gap between the capacity and MCCR. This benefit is present regardless of the utilized pulse shape, including the ideal sinc-pulse, and is unique to the FBL regime. Instead of increasing MCCR for fixed block error rates, FTN can alternatively lower the block error rates for fixed channel coding rates. These results imply that FTN can lower the penalty from limited channel coding over short blocklength and can improve the performance and reliability of short packet communications.
FPGAs are rarely mentioned when discussing the implementation of large machine learning applications, such as Large Language Models (LLMs), in the data center. There has been much evidence showing that single FPGAs can be competitive with GPUs in performance for some computations, especially for low latency, and often much more efficient when power is considered. This suggests that there is merit to exploring the use of multiple FPGAs for large machine learning applications. The challenge with using multiple FPGAs is that there is no commonly-accepted flow for developing and deploying multi-FPGA applications, i.e., there are no tools to describe a large application, map it to multiple FPGAs and then deploy the application on a multi-FPGA platform. In this paper, we explore the feasibility of implementing large transformers using multiple FPGAs by developing a scalable multi-FPGA platform and some tools to map large applications to the platform. We validate our approach by designing an efficient multi-FPGA version of the I-BERT transformer and implement one encoder using six FPGAs as a working proof-of-concept to show that our platform and tools work. Based on our proof-of-concept prototype and the estimations of performance using the latest FPGAs compared to GPUs, we conclude that there can be a place for FPGAs in the world of large machine learning applications. We demonstrate a promising first step that shows that with the right infrastructure and tools it is reasonable to continue to explore the possible benefits of using FPGAs for applications such as LLMs.
The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question answering or machine translation). However, it builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. Moreover, it is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime. The first goal of this thesis is to characterize the different forms this shift can take in the context of natural language processing, and propose benchmarks and evaluation metrics to measure its effect on current deep learning architectures. We then proceed to take steps to mitigate the effect of distributional shift on NLP models. To this end, we develop methods based on parametric reformulations of the distributionally robust optimization framework. Empirically, we demonstrate that these approaches yield more robust models as demonstrated on a selection of realistic problems. In the third and final part of this thesis, we explore ways of efficiently adapting existing models to new domains or tasks. Our contribution to this topic takes inspiration from information geometry to derive a new gradient update rule which alleviate catastrophic forgetting issues during adaptation.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191