Deep learning recommendation models have grown to the terabyte scale. Traditional serving schemes--that load entire models to a single server--are unable to support this scale. One approach to support this scale is with distributed serving, or distributed inference, which divides the memory requirements of a single large model across multiple servers.
This work is a first-step for the systems research community to develop novel model-serving solutions, given the huge system design space. Large-scale deep recommender systems are a novel workload and vital to study, as they consume up to 79% of all inference cycles in the data center. To that end, this work describes and characterizes scale-out deep learning recommendation inference using data-center serving infrastructure. This work specifically explores latency-bounded inference systems, compared to the throughput-oriented training systems of other recent works. We find that the latency and compute overheads of distributed inference are largely a result of a model's static embedding table distribution and sparsity of input inference requests. We further evaluate three embedding table mapping strategies of three DLRM-like models and specify challenging design trade-offs in terms of end-to-end latency, compute overhead, and resource efficiency. Overall, we observe only a marginal latency overhead when the data-center scale recommendation models are served with the distributed inference manner--P99 latency is increased by only 1% in the best case configuration. The latency overheads are largely a result of the commodity infrastructure used and the sparsity of embedding tables. Even more encouragingly, we also show how distributed inference can account for efficiency improvements in data-center scale recommendation serving.
Shanghai Jiao Tong University（上海交通大学）；University of Technology Sydney（悉尼科技大学）
An excessive number of customers often leads to a degradation in service quality. However, the capacity constraints of services are ignored by recommender systems, which may lead to unsatisfactory recommendation. This problem can be solved by limiting the number of users who receive the recommendation for a service, but this may be viewed as unfair. In this paper, we propose a novel metric Top-N Fairness to measure the individual fairness of multi-round recommendations of services with capacity constraints. By considering the fact that users are often only affected by top-ranked items in a rec…
Arizona State University（亚利桑那州立大学）；Facebook, Inc.（Facebook公司）
Deep learning recommendation systems at scale have provided remarkable gains through increasing model capacity (i.e. wider and deeper neural networks), but it comes at significant training cost and infrastructure cost. Model pruning is an effective technique to reduce computation overhead for deep neural networks by removing redundant parameters. However, modern recommendation systems are still thirsty for model capacity due to the demand for handling big data. Thus, pruning a recommendation model at scale results in a smaller model capacity and consequently lower accuracy. To reduce computati…
Recommendation systems are of crucial importance for a variety of modern apps and web services, such as news feeds, social networks, e-commerce, search, etc. To achieve peak prediction accuracy, modern recommendation models combine deep learning with terabyte-scale embedding tables to obtain a fine-grained representation of the underlying data. Traditional inference serving architectures require deploying the whole model to standalone servers, which is infeasible at such massive scale. In this paper, we provide insights into the intriguing and challenging inference domain of online recommendat…
ETH Zurich（苏黎世联邦理工学院）；Columbia University（哥伦比亚大学）；Alibaba Group（阿里巴巴集团）
Deep neural networks are widely used in personalized recommendation systems. Unlike regular DNN inference workloads, recommendation inference is memory-bound due to the many random memory accesses needed to lookup the embedding tables. The inference is also heavily constrained in terms of latency because producing a recommendation for a user must be done in about tens of milliseconds. In this paper, we propose MicroRec, a high-performance inference engine for recommendation systems. MicroRec accelerates recommendation inference by (1) redesigning the data structures involved in the embeddings …
Relevance and diversity are both important to the success of recommender systems, as they help users to discover from a large pool of items a compact set of candidates that are not only interesting but exploratory as well. The challenge is that relevance and diversity usually act as two competing objectives in conventional recommender systems, which necessities the classic trade-off between exploitation and exploration. Traditionally, higher diversity often means sacrifice on relevance and vice versa. We propose a new approach, heterogeneous inference, which extends the general collaborative f…
University of California Berkeley（加州大学伯克利分校）；University of Michigan（密歇根大学）
Recommender systems play a key role in shaping modern web ecosystems. These systems alternate between (1) making recommendations (2) collecting user responses to these recommendations, and (3) retraining the recommendation algorithm based on this feedback. During this process the recommender system influences the user behavioral data that is subsequently used to update it, thus creating a feedback loop. Recent work has shown that feedback loops may compromise recommendation quality and homogenize user behavior, raising ethical and performance concerns when deploying recommender systems. To add…
Facebook（脸书）；University of Colorado, Boulder（科罗拉多大学博尔德分校）；Google Research（谷歌研究院）；University of Minnesota（明尼苏达大学）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；Netflix（奈飞）
Deep learning-based recommendation models are used pervasively and broadly, for example, to recommend movies, products, or other information most relevant to users, in order to enhance the user experience. Among various application domains which have received significant industry and academia research attention, such as image classification, object detection, language and speech translation, the performance of deep learning-based recommendation models is less well explored, even though recommendation tasks unarguably represent significant AI inference cycles at large-scale datacenter fleets. T…
With growing consumer adoption of online grocery shopping through platforms such as Amazon Fresh, Instacart, and Walmart Grocery, there is a pressing business need to provide relevant recommendations throughout the customer journey. In this paper, we introduce a production within-basket grocery recommendation system, RTT2Vec, which generates real-time personalized product recommendations to supplement the user's current grocery basket. We conduct extensive offline evaluation of our system and demonstrate a 9.4% uplift in prediction metrics over baseline state-of-the-art within-basket recommend…
Recommender systems are critical tools to match listings and travelers in two-sided vacation rental marketplaces. Such systems require high capacity to extract user preferences for items from implicit signals at scale. To learn those preferences, we propose a Simple Deep Personalized Recommendation System to compute travelers' conditional embeddings. Our method combines listing embeddings in a supervised structure to build short-term historical context to personalize recommendations for travelers. Deployed in the production environment, this approach is computationally efficient and scalable, …
Tremendous success of machine learning (ML) and the unabated growth in ML model complexity motivated many ML-specific designs in both CPU and accelerator architectures to speed up the model inference. While these architectures are diverse, highly optimized low-precision arithmetic is a component shared by most. Impressive compute throughputs are indeed often exhibited by these architectures on benchmark ML models. Nevertheless, production models such as recommendation systems important to Facebook's personalization services are demanding and complex: These systems must serve billions of users …
We are constantly using recommender systems, often without even noticing. They build a profile of our person in order to recommend the content we will most likely be interested in. The data representing the users, their interactions with the system or the products may come from different sources and be of a various nature. Our goal is to use a multi-view learning approach to improve our recommender system and improve its capacity to manage multi-view data. We propose a comparative study between several state-of-the-art multi-view models applied to our industrial data. Our study demonstrates th…
The business objectives of recommenders, such as increasing sales, are aligned with the causal effect of recommendations. Previous recommenders targeting for the causal effect employ the inverse propensity scoring (IPS) in causal inference. However, IPS is prone to suffer from high variance. The matching estimator is another representative method in causal inference field. It does not use propensity and hence free from the above variance problem. In this work, we unify traditional neighborhood recommendation methods with the matching estimator, and develop robust ranking methods for the causal…
BEYOND Centre, IAASARS, National Observatory of Athens（雅典国家天文台 IAASARS BEYOND 中心）；Wageningen University and Research（瓦赫宁根大学与研究中心）；Hellenic Agricultural Organization ELGO DIMITRA（希腊农业组织 ELGO DIMITRA）
In contrast to the rapid digitalization of several industries, agriculture suffers from low adoption of smart farming tools. While AI-driven digital agriculture tools can offer high-performing predictive functionalities, they lack tangible quantitative evidence on their benefits to the farmers. Field experiments can derive such evidence, but are often costly, time consuming and hence limited in scope and scale of application. To this end, we propose an observational causal inference framework for the empirical evaluation of the impact of digital tools on target farm performance indicators (e.g…
KTH Royal Institute of Technology（瑞典皇家理工学院）；Hive Streaming AB（Hive Streaming公司）；Maastricht University（马斯特里赫特大学）；University of Amsterdam（阿姆斯特丹大学）
Conversational recommendation systems have recently gain a lot of attention, as users can continuously interact with the system over multiple conversational turns. However, conversational recommendation systems are based on complex neural architectures, thus the training cost of such models is high. To shed light on the high computational training time of state-of-the art conversational models, we examine five representative strategies and demonstrate this issue. Furthermore, we discuss possible ways to cope with the high training cost following knowledge distillation strategies, where we deta…
While providing low latency is a fundamental requirement in deploying recommendation services, achieving high resource utility is also crucial in cost-effectively maintaining the datacenter. Co-locating multiple workers of a model is an effective way to maximize query-level parallelism and server throughput, but the interference caused by concurrent workers at shared resources can prevent server queries from meeting its SLA. Hera utilizes the heterogeneous memory requirement of multi-tenant recommendation models to intelligently determine a productive set of co-located models and its resource …
Neural personalized recommendation is the corner-stone of a wide collection of cloud services and products, constituting significant compute demand of the cloud infrastructure. Thus, improving the execution efficiency of neural recommendation directly translates into infrastructure capacity saving. In this paper, we devise a novel end-to-end modeling infrastructure, DeepRecInfra, that adopts an algorithm and system co-design methodology to custom-design systems for recommendation use cases. Leveraging the insights from the recommendation characterization, a new dynamic scheduler, DeepRecSched,…
Personalized recommendation is an important class of deep-learning applications that powers a large collection of internet services and consumes a considerable amount of datacenter resources. As the scale of production-grade recommendation systems continues to grow, optimizing their serving performance and efficiency in a heterogeneous datacenter is important and can translate into infrastructure capacity saving. In this paper, we propose Hercules, an optimized framework for personalized recommendation inference serving that targets diverse industry-representative models and cloud-scale hetero…
Harvard University（哈佛大学）；Facebook AI Research（脸书人工智能研究院）
Deep learning recommendation systems must provide high quality, personalized content under strict tail-latency targets and high system loads. This paper presents RecPipe, a system to jointly optimize recommendation quality and inference performance. Central to RecPipe is decomposing recommendation models into multi-stage pipelines to maintain quality while reducing compute complexity and exposing distinct parallelism opportunities. RecPipe implements an inference scheduler to map multi-stage recommendation engines onto commodity, heterogeneous platforms (e.g., CPUs, GPUs).While the hardware-aw…
Personalized recommendation systems leverage deep learning models and account for the majority of data center AI cycles. Their performance is dominated by memory-bound sparse embedding operations with unique irregular memory access patterns that pose a fundamental challenge to accelerate. This paper proposes a lightweight, commodity DRAM compliant, near-memory processing solution to accelerate personalized recommendation inference. The in-depth characterization of production-grade recommendation models shows that embedding operations with high model-, operator- and data-level parallelism lead …
