Multi-antenna coded caching is known to combine a global caching gain that is proportional to the cumulative cache size found across the network, with an additional spatial multiplexing gain that stems from using multiple transmitting antennas. However, a closer look reveals two severe bottlenecks; the well-known exponential subpacketization bottleneck that dramatically reduces performance when the communicated file sizes are finite, and the considerable optimization complexity of beamforming multicast messages when the SNR is finite. We here present an entirely novel caching scheme, termed \emph{cyclic multi-antenna coded caching}, whose unique structure allows for the resolution of the above bottlenecks in the crucial regime of many transmit antennas. For this regime, where the multiplexing gain can exceed the coding gain, our new algorithm is the first to achieve the exact one-shot linear optimal DoF with a subpacketization complexity that scales only linearly with the number of users, and the first to benefit from a multicasting structure that allows for exploiting uplink-downlink duality in order to yield optimized beamformers ultra-fast. In the end, our novel solution provides excellent performance for networks with finite SNR, finite file sizes, and many users.
相關內容
Recent research investigates the decode-and-forward (DF) relaying for mixed radio frequency (RF) and terahertz (THz) wireless links with zero-boresight pointing errors. In this letter, we analyze the performance of a fixed-gain amplify-and-forward (AF) relaying for the RF-THz link to interface the access network on the RF technology with wireless THz transmissions. We develop probability density function (PDF) and cumulative distribution function (CDF) of the end-to-end SNR for the relay-assisted system in terms of bivariate Fox's H function considering $\alpha$-$\mu$ fading for the THz system with non-zero boresight pointing errors and $\alpha$-$\kappa$-$\mu$ shadowed ($\alpha$-KMS) fading model for the RF link. Using the derived PDF and CDF, we present exact analytical expressions of the outage probability, average bit-error-rate (BER), and ergodic capacity of the considered system. We also analyze the outage probability and average BER asymptotically for a better insight into the system behavior at high SNR. We use simulations to compare the performance of the AF relaying having a semi-blind gain factor with the recently proposed DF relaying for THz-RF transmissions.
In multiuser communication systems, user scheduling and beamforming design are two fundamental problems, which are usually investigated separately in the existing literature. In this work, we focus on the joint optimization of user scheduling and beamforming design with the goal of maximizing the set cardinality of scheduled users. Observing that this problem is computationally challenging due to the non-convex objective function and coupled constraints in continuous and binary variables. To tackle these difficulties, we first propose an iterative optimization algorithm (IOA) relying on the successive convex approximation and uplink-downlink duality theory. Then, motivated by IOA and graph neural networks, a joint user scheduling and power allocation network (JEEPON) is developed to address the investigated problem in an unsupervised manner. The effectiveness of IOA and JEEPON is verified by various numerical results, and the latter achieves a close performance but lower complexity compared with IOA and the greedy-based algorithm. Remarkably, the proposed JEEPON is also competitive in terms of the generalization ability in dynamic wireless network scenarios.
Recently, RobustBench (Croce et al. 2020) has become a widely recognized benchmark for the adversarial robustness of image classification networks. In its most commonly reported sub-task, RobustBench evaluates and ranks the adversarial robustness of trained neural networks on CIFAR10 under AutoAttack (Croce and Hein 2020b) with l-inf perturbations limited to eps = 8/255. With leading scores of the currently best performing models of around 60% of the baseline, it is fair to characterize this benchmark to be quite challenging. Despite its general acceptance in recent literature, we aim to foster discussion about the suitability of RobustBench as a key indicator for robustness which could be generalized to practical applications. Our line of argumentation against this is two-fold and supported by excessive experiments presented in this paper: We argue that I) the alternation of data by AutoAttack with l-inf, eps = 8/255 is unrealistically strong, resulting in close to perfect detection rates of adversarial samples even by simple detection algorithms and human observers. We also show that other attack methods are much harder to detect while achieving similar success rates. II) That results on low-resolution data sets like CIFAR10 do not generalize well to higher resolution images as gradient-based attacks appear to become even more detectable with increasing resolutions.
As the heart of a search engine, the ranking system plays a crucial role in satisfying users' information demands. More recently, neural rankers fine-tuned from pre-trained language models (PLMs) establish state-of-the-art ranking effectiveness. However, it is nontrivial to directly apply these PLM-based rankers to the large-scale web search system due to the following challenging issues:(1) the prohibitively expensive computations of massive neural PLMs, especially for long texts in the web-document, prohibit their deployments in an online ranking system that demands extremely low latency;(2) the discrepancy between existing ranking-agnostic pre-training objectives and the ad-hoc retrieval scenarios that demand comprehensive relevance modeling is another main barrier for improving the online ranking system;(3) a real-world search engine typically involves a committee of ranking components, and thus the compatibility of the individually fine-tuned ranking model is critical for a cooperative ranking system. In this work, we contribute a series of successfully applied techniques in tackling these exposed issues when deploying the state-of-the-art Chinese pre-trained language model, i.e., ERNIE, in the online search engine system. We first articulate a novel practice to cost-efficiently summarize the web document and contextualize the resultant summary content with the query using a cheap yet powerful Pyramid-ERNIE architecture. Then we endow an innovative paradigm to finely exploit the large-scale noisy and biased post-click behavioral data for relevance-oriented pre-training. We also propose a human-anchored fine-tuning strategy tailored for the online ranking system, aiming to stabilize the ranking signals across various online components. Extensive offline and online experimental results show that the proposed techniques significantly boost the search engine's performance.
Recommender systems (RS), which have been an essential part in a wide range of applications, can be formulated as a matrix completion (MC) problem. To boost the performance of MC, matrix completion with side information, called inductive matrix completion (IMC), was further proposed. In real applications, the factorized version of IMC is more favored due to its efficiency of optimization and implementation. Regarding the factorized version, traditional IMC method can be interpreted as learning an individual representation for each feature, which is independent from each other. Moreover, representations for the same features are shared across all users/items. However, the independent characteristic for features and shared characteristic for the same features across all users/items may limit the expressiveness of the model. The limitation also exists in variants of IMC, such as deep learning based IMC models. To break the limitation, we generalize recent advances of self-attention mechanism to IMC and propose a context-aware model called collaborative self-attention (CSA), which can jointly learn context-aware representations for features and perform inductive matrix completion process. Extensive experiments on three large-scale datasets from real RS applications demonstrate effectiveness of CSA.
The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyper-parameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normalization between the residual blocks, the expected gradients of the parameters near the output layer are large. Therefore, using a large learning rate on those gradients makes the training unstable. The warm-up stage is practically helpful for avoiding this problem. On the other hand, our theory also shows that if the layer normalization is put inside the residual blocks (recently proposed as Pre-LN Transformer), the gradients are well-behaved at initialization. This motivates us to remove the warm-up stage for the training of Pre-LN Transformers. We show in our experiments that Pre-LN Transformers without the warm-up stage can reach comparable results with baselines while requiring significantly less training time and hyper-parameter tuning on a wide range of applications.
Training large deep neural networks on massive datasets is computationally very challenging. There has been recent surge in interest in using large batch stochastic optimization methods to tackle this issue. The most prominent algorithm in this line of research is LARS, which by employing layerwise adaptive learning rates trains ResNet on ImageNet in a few minutes. However, LARS performs poorly for attention models like BERT, indicating that its performance gains are not consistent across tasks. In this paper, we first study a principled layerwise adaptation strategy to accelerate training of deep neural networks using large mini-batches. Using this strategy, we develop a new layerwise adaptive large batch optimization technique called LAMB; we then provide convergence analysis of LAMB as well as LARS, showing convergence to a stationary point in general nonconvex settings. Our empirical results demonstrate the superior performance of LAMB across various tasks such as BERT and ResNet-50 training with very little hyperparameter tuning. In particular, for BERT training, our optimizer enables use of very large batch sizes of 32868 without any degradation of performance. By increasing the batch size to the memory limit of a TPUv3 Pod, BERT training time can be reduced from 3 days to just 76 minutes (Table 1).
We study learning of a matching model for response selection in retrieval-based dialogue systems. The problem is equally important with designing the architecture of a model, but is less explored in existing literature. To learn a robust matching model from noisy training data, we propose a general co-teaching framework with three specific teaching strategies that cover both teaching with loss functions and teaching with data curriculum. Under the framework, we simultaneously learn two matching models with independent training sets. In each iteration, one model transfers the knowledge learned from its training set to the other model, and at the same time receives the guide from the other model on how to overcome noise in training. Through being both a teacher and a student, the two models learn from each other and get improved together. Evaluation results on two public data sets indicate that the proposed learning approach can generally and significantly improve the performance of existing matching models.
We present collaborative similarity embedding (CSE), a unified framework that exploits comprehensive collaborative relations available in a user-item bipartite graph for representation learning and recommendation. In the proposed framework, we differentiate two types of proximity relations: direct proximity and k-th order neighborhood proximity. While learning from the former exploits direct user-item associations observable from the graph, learning from the latter makes use of implicit associations such as user-user similarities and item-item similarities, which can provide valuable information especially when the graph is sparse. Moreover, for improving scalability and flexibility, we propose a sampling technique that is specifically designed to capture the two types of proximity relations. Extensive experiments on eight benchmark datasets show that CSE yields significantly better performance than state-of-the-art recommendation methods.
Model-based methods for recommender systems have been studied extensively in recent years. In systems with large corpus, however, the calculation cost for the learnt model to predict all user-item preferences is tremendous, which makes full corpus retrieval extremely difficult. To overcome the calculation barriers, models such as matrix factorization resort to inner product form (i.e., model user-item preference as the inner product of user, item latent factors) and indexes to facilitate efficient approximate k-nearest neighbor searches. However, it still remains challenging to incorporate more expressive interaction forms between user and item features, e.g., interactions through deep neural networks, because of the calculation cost. In this paper, we focus on the problem of introducing arbitrary advanced models to recommender systems with large corpus. We propose a novel tree-based method which can provide logarithmic complexity w.r.t. corpus size even with more expressive models such as deep neural networks. Our main idea is to predict user interests from coarse to fine by traversing tree nodes in a top-down fashion and making decisions for each user-node pair. We also show that the tree structure can be jointly learnt towards better compatibility with users' interest distribution and hence facilitate both training and prediction. Experimental evaluations with two large-scale real-world datasets show that the proposed method significantly outperforms traditional methods. Online A/B test results in Taobao display advertising platform also demonstrate the effectiveness of the proposed method in production environments.
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