Super-resolution (SR) networks have been investigated for a while, with their mobile and lightweight versions gaining noticeable popularity recently. Quantization, the procedure of decreasing the precision of network parameters (mostly FP32 to INT8), is also utilized in SR networks for establishing mobile compatibility. This study focuses on a very important but mostly overlooked post-training quantization (PTQ) step: representative dataset (RD), which adjusts the quantization range for PTQ. We propose a novel pipeline (clip-free quantization pipeline, CFQP) backed up with extensive experimental justifications to cleverly augment RD images by only using outputs of the FP32 model. Using the proposed pipeline for RD, we can successfully eliminate unwanted clipped activation layers, which nearly all mobile SR methods utilize to make the model more robust to PTQ in return for a large overhead in runtime. Removing clipped activations with our method significantly benefits overall increased stability, decreased inference runtime up to 54% on some SR models, better visual quality results compared to INT8 clipped models - and outperforms even some FP32 non-quantized models, both in runtime and visual quality, without the need for retraining with clipped activation.
相關內容
Star-join query is the fundamental task in data warehouse and has wide applications in On-line Analytical Processing (OLAP) scenarios. Due to the large number of foreign key constraints and the asymmetric effect in the neighboring instance between the fact and dimension tables, even those latest DP efforts specifically designed for join, if directly applied to star-join query, will suffer from extremely large estimation errors and expensive computational cost. In this paper, we are thus motivated to propose DP-starJ, a novel Differentially Private framework for star-Join queries. DP-starJ consists of a series of strategies tailored to specific features of star-join, including 1) we unveil the different effect of fact and dimension tables on the neighboring database instances, and accordingly revisit the definitions tailored to different cases of star-join; 2) we propose Predicate Mechanism (PM), which utilizes predicate perturbation to inject noise into the join procedure instead of the results; 3) to further boost the robust performance, we propose a DP-compliant star-join algorithm for various types of star-join tasks based on PM. We provide both theoretical analysis and empirical study, which demonstrate the superiority of the proposed methods over the state-of-the-art solutions in terms of accuracy, efficiency, and scalability.
The widespread adoption of encryption in network protocols has significantly improved the overall security of many Internet applications. However, these protocols cannot prevent network side-channel leaks -- leaks of sensitive information through the sizes and timing of network packets. We present NetShaper, a system that mitigates such leaks based on the principle of traffic shaping. NetShaper's traffic shaping provides differential privacy guarantees while adapting to the prevailing workload and congestion condition, and allows configuring a tradeoff between privacy guarantees, bandwidth and latency overheads. Furthermore, NetShaper provides a modular and portable tunnel endpoint design that can support diverse applications. We present a middlebox-based implementation of NetShaper and demonstrate its applicability in a video streaming and a web service application.
Private 5G networks will soon be ubiquitous across the future-generation smart wireless access infrastructures hosting a wide range of performance-critical applications. A high-performing User Plane Function (UPF) in the data plane is critical to achieving such stringent performance goals, as it governs fast packet processing and supports several key control-plane operations. Based on a private 5G prototype implementation and analysis, it is imperative to perform dynamic resource management and orchestration at the UPF. This paper leverages Mobile Edge Cloud-Intelligent Agent (MEC-IA), a logically centralized entity that proactively distributes resources at UPF for various service types, significantly reducing the tail latency experienced by the user requests while maximizing resource utilization. Extending the MEC-IA functionality to MEC layers further incurs data plane latency reduction. Based on our extensive simulations, under skewed uRLLC traffic arrival, the MEC-IA assisted bestfit UPF-MEC scheme reduces the worst-case latency of UE requests by up to 77.8% w.r.t. baseline. Additionally, the system can increase uRLLC connectivity gain by 2.40x while obtaining 40% CapEx savings.
By classifying infinite-width neural networks and identifying the *optimal* limit, Tensor Programs IV and V demonstrated a universal way, called $\mu$P, for *widthwise hyperparameter transfer*, i.e., predicting optimal hyperparameters of wide neural networks from narrow ones. Here we investigate the analogous classification for *depthwise parametrizations* of deep residual networks (resnets). We classify depthwise parametrizations of block multiplier and learning rate by their infinite-width-then-depth limits. In resnets where each block has only one layer, we identify a unique optimal parametrization, called Depth-$\mu$P that extends $\mu$P and show empirically it admits depthwise hyperparameter transfer. We identify *feature diversity* as a crucial factor in deep networks, and Depth-$\mu$P can be characterized as maximizing both feature learning and feature diversity. Exploiting this, we find that absolute value, among all homogeneous nonlinearities, maximizes feature diversity and indeed empirically leads to significantly better performance. However, if each block is deeper (such as modern transformers), then we find fundamental limitations in all possible infinite-depth limits of such parametrizations, which we illustrate both theoretically and empirically on simple networks as well as Megatron transformer trained on Common Crawl.
Data silos create barriers in accessing and utilizing data dispersed over networks. Directly sharing data easily suffers from the long downloading time, the single point failure and the untraceable data usage. In this paper, we present Minerva, a peer-to-peer cross-cluster data query system based on InterPlanetary File System (IPFS). Minerva makes use of the distributed Hash table (DHT) lookup to pinpoint the locations that store content chunks. We theoretically model the DHT query delay and introduce the fat Merkle tree structure as well as the DHT caching to reduce it. We design the query plan for read and write operations on top of Apache Drill that enables the collaborative query with decentralized workers. We conduct comprehensive experiments on Minerva, and the results show that Minerva achieves up to $2.08 \times$ query performance acceleration compared to the original IPFS data query, and could complete data analysis queries on the Internet-like environments within an average latency of $0.615$ second. With collaborative query, Minerva could perform up to $1.39 \times$ performance acceleration than centralized query with raw data shipment.
In the face of rising global demand for audio/video meetings, managing traffic across geographically distributed (geo-distributed) data centers presents a significant challenge due to the dynamic and limited nature of inter-DC network performance. Facing these issues, this paper introduces two novel techniques, VCRoute and WMJitter, to optimize the performance of geo-distributed video conferencing systems. VCRoute is a routing method designed for video conferencing data packets. It treats the routing problem as a Multi-Armed Bandit issue, and utilizes a tailored Thompson Sampling algorithm for resolution. Unlike traditional approaches, VCRoute uses predicted end-to-end latency as the routing selection reward for each packet, enabling effective and timely end-to-end latency optimization. In conjunction with VCRoute, we present WMJitter, a watermark-based mechanism for managing network jitter. Leveraging a window-based statistic method, WMJitter enables real-time network jitter estimation, leading to significant reductions in end-to-end delay and an improved balance between latency and loss rate. Evaluations based on real geo-distributed network performance demonstrate the effectiveness and scalability of VCRoute and WMJitter, offering robust solutions for optimizing video conferencing systems in geo-distributed settings.
We consider low-latency image transmission over a noisy wireless channel when correlated side information is present only at the receiver side (the Wyner-Ziv scenario). In particular, we are interested in developing practical schemes using a data-driven joint source-channel coding (JSCC) approach, which has been previously shown to outperform conventional separation-based approaches in the practical finite blocklength regimes, and to provide graceful degradation with channel quality. We propose a novel neural network architecture that incorporates the decoder-only side information at multiple stages at the receiver side. Our results demonstrate that the proposed method succeeds in integrating the side information, yielding improved performance at all channel noise levels in terms of the various distortion criteria considered here, especially at low channel signal-to-noise ratios (SNRs) and small bandwidth ratios (BRs). We also provide the source code of the proposed method to enable further research and reproducibility of the results.
In recent years, Federated Learning (FL) has shown significant advancements in its ability to perform various natural language processing (NLP) tasks. This work focuses on applying personalized FL for on-device language modeling. Due to limitations of memory and latency, these models cannot support the complexity of sub-word tokenization or beam search decoding, resulting in the decision to deploy a closed-vocabulary language model. However, closed-vocabulary models are unable to handle out-of-vocabulary (OOV) words belonging to specific users. To address this issue, We propose a novel technique called "OOV expansion" that improves OOV coverage and increases model accuracy while minimizing the impact on memory and latency. This method introduces a personalized "OOV adapter" that effectively transfers knowledge from a central model and learns word embedding for personalized vocabulary. OOV expansion significantly outperforms standard FL personalization methods on a set of common FL benchmarks.
Vast amount of data generated from networks of sensors, wearables, and the Internet of Things (IoT) devices underscores the need for advanced modeling techniques that leverage the spatio-temporal structure of decentralized data due to the need for edge computation and licensing (data access) issues. While federated learning (FL) has emerged as a framework for model training without requiring direct data sharing and exchange, effectively modeling the complex spatio-temporal dependencies to improve forecasting capabilities still remains an open problem. On the other hand, state-of-the-art spatio-temporal forecasting models assume unfettered access to the data, neglecting constraints on data sharing. To bridge this gap, we propose a federated spatio-temporal model -- Cross-Node Federated Graph Neural Network (CNFGNN) -- which explicitly encodes the underlying graph structure using graph neural network (GNN)-based architecture under the constraint of cross-node federated learning, which requires that data in a network of nodes is generated locally on each node and remains decentralized. CNFGNN operates by disentangling the temporal dynamics modeling on devices and spatial dynamics on the server, utilizing alternating optimization to reduce the communication cost, facilitating computations on the edge devices. Experiments on the traffic flow forecasting task show that CNFGNN achieves the best forecasting performance in both transductive and inductive learning settings with no extra computation cost on edge devices, while incurring modest communication cost.
Generative adversarial networks (GANs) have been extensively studied in the past few years. Arguably their most significant impact has been in the area of computer vision where great advances have been made in challenges such as plausible image generation, image-to-image translation, facial attribute manipulation and similar domains. Despite the significant successes achieved to date, applying GANs to real-world problems still poses significant challenges, three of which we focus on here. These are: (1) the generation of high quality images, (2) diversity of image generation, and (3) stable training. Focusing on the degree to which popular GAN technologies have made progress against these challenges, we provide a detailed review of the state of the art in GAN-related research in the published scientific literature. We further structure this review through a convenient taxonomy we have adopted based on variations in GAN architectures and loss functions. While several reviews for GANs have been presented to date, none have considered the status of this field based on their progress towards addressing practical challenges relevant to computer vision. Accordingly, we review and critically discuss the most popular architecture-variant, and loss-variant GANs, for tackling these challenges. Our objective is to provide an overview as well as a critical analysis of the status of GAN research in terms of relevant progress towards important computer vision application requirements. As we do this we also discuss the most compelling applications in computer vision in which GANs have demonstrated considerable success along with some suggestions for future research directions. Code related to GAN-variants studied in this work is summarized on //github.com/sheqi/GAN_Review.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191