CascadeServe: Unlocking Model Cascades for Inference Serving

Machine learning (ML) models are increasingly deployed to production, calling for efficient inference serving systems. Efficient inference serving is complicated by two challenges: (i) ML models incur high computational costs, and (ii) the request arrival rates of practical applications have frequent, high, and sudden variations which make it hard to correctly provision hardware. Model cascades are positioned to tackle both of these challenges, as they (i) save work while maintaining accuracy, and (ii) expose a high-resolution trade-off between work and accuracy, allowing for fine-grained adjustments to request arrival rates. Despite their potential, model cascades haven't been used inside an online serving system. This comes with its own set of challenges, including workload adaption, model replication onto hardware, inference scheduling, request batching, and more. In this work, we propose CascadeServe, which automates and optimizes end-to-end inference serving with cascades. CascadeServe operates in an offline and online phase. In the offline phase, the system pre-computes a gear plan that specifies how to serve inferences online. In the online phase, the gear plan allows the system to serve inferences while making near-optimal adaptations to the query load at negligible decision overheads. We find that CascadeServe saves 2-3x in cost across a wide spectrum of the latency-accuracy space when compared to state-of-the-art baselines on different workloads.

A Declarative System for Optimizing AI Workloads

Modern AI models provide the key to a long-standing dream: processing analytical queries about almost any kind of data. Until recently, it was difficult and expensive to extract facts from company documents, data from scientific papers, or insights from image and video corpora. Today's models can accomplish these tasks with high accuracy. However, a programmer who wants to answer a substantive AI-powered query must orchestrate large numbers of models, prompts, and data operations. For even a single query, the programmer has to make a vast number of decisions such as the choice of model, the right inference method, the most cost-effective inference hardware, the ideal prompt design, and so on. The optimal set of decisions can change as the query changes and as the rapidly-evolving technical landscape shifts. In this paper we present Palimpzest, a system that enables anyone to process AI-powered analytical queries simply by defining them in a declarative language. The system uses its cost optimization framework -- which explores the search space of AI models, prompting techniques, and related foundation model optimizations -- to implement the query with the best trade-offs between runtime, financial cost, and output data quality. We describe the workload of AI-powered analytics tasks, the optimization methods that Palimpzest uses, and the prototype system itself. We evaluate Palimpzest on tasks in Legal Discovery, Real Estate Search, and Medical Schema Matching. We show that even our simple prototype offers a range of appealing plans, including one that is 3.3x faster, 2.9x cheaper, and offers better data quality than the baseline method. With parallelism enabled, Palimpzest can produce plans with up to a 90.3x speedup at 9.1x lower cost relative to a single-threaded GPT-4 baseline, while obtaining an F1-score within 83.5% of the baseline. These require no additional work by the user.

Tensor-based Graph Learning with Consistency and Specificity for Multi-view Clustering

In the context of multi-view clustering, graph learning is recognized as a crucial technique, which generally involves constructing an adaptive neighbor graph based on probabilistic neighbors, and then learning a consensus graph to for clustering. However, they are confronted with two limitations. Firstly, they often rely on Euclidean distance to measure similarity when constructing the adaptive neighbor graph, which proves inadequate in capturing the intrinsic structure among data points in practice. Secondly, most of these methods focus solely on consensus graph, ignoring unique information from each view. Although a few graph-based studies have considered using specific information as well, the modelling approach employed does not exclude the noise impact from the specific component. To this end, we propose a novel tensor-based multi-view graph learning framework that simultaneously considers consistency and specificity, while effectively eliminating the influence of noise. Specifically, we calculate similarity distance on the Stiefel manifold to preserve the intrinsic properties of data. By making an assumption that the learned neighbor graph of each view comprises a consistent part, a specific part, and a noise part, we formulate a new tensor-based target graph learning paradigm for noise-free graph fusion. Owing to the benefits of tensor singular value decomposition (t-SVD) in uncovering high-order correlations, this model is capable of achieving a complete understanding of the target graph. Furthermore, we derive an algorithm to address the optimization problem. Experiments on six datasets have demonstrated the superiority of our method. We have released the source code on https://github.com/lshi91/CSTGL-Code.

Nonlinear subspace clustering by functional link neural networks

Nonlinear subspace clustering based on a feed-forward neural network has been demonstrated to provide better clustering accuracy than some advanced subspace clustering algorithms. While this approach demonstrates impressive outcomes, it involves a balance between effectiveness and computational cost. In this study, we employ a functional link neural network to transform data samples into a nonlinear domain. Subsequently, we acquire a self-representation matrix through a learning mechanism that builds upon the mapped samples. As the functional link neural network is a single-layer neural network, our proposed method achieves high computational efficiency while ensuring desirable clustering performance. By incorporating the local similarity regularization to enhance the grouping effect, our proposed method further improves the quality of the clustering results. Additionally, we introduce a convex combination subspace clustering scheme, which combining a linear subspace clustering method with the functional link neural network subspace clustering approach. This combination approach allows for a dynamic balance between linear and nonlinear representations. Extensive experiments confirm the advancement of our methods. The source code will be released on https://lshi91.github.io/ soon.

Enhanced Latent Multi-view Subspace Clustering

Latent multi-view subspace clustering has been demonstrated to have desirable clustering performance. However, the original latent representation method vertically concatenates the data matrices from multiple views into a single matrix along the direction of dimensionality to recover the latent representation matrix, which may result in an incomplete information recovery. To fully recover the latent space representation, we in this paper propose an Enhanced Latent Multi-view Subspace Clustering (ELMSC) method. The ELMSC method involves constructing an augmented data matrix that enhances the representation of multi-view data. Specifically, we stack the data matrices from various views into the block-diagonal locations of the augmented matrix to exploit the complementary information. Meanwhile, the non-block-diagonal entries are composed based on the similarity between different views to capture the consistent information. In addition, we enforce a sparse regularization for the non-diagonal blocks of the augmented self-representation matrix to avoid redundant calculations of consistency information. Finally, a novel iterative algorithm based on the framework of Alternating Direction Method of Multipliers (ADMM) is developed to solve the optimization problem for ELMSC. Extensive experiments on real-world datasets demonstrate that our proposed ELMSC is able to achieve higher clustering performance than some state-of-art multi-view clustering methods.

Quantized-but-uncoded Distributed Detection (QDD) with Unreliable Reporting Channels

Distributed detection primarily centers around two approaches: Unquantized Distributed Detection (UDD), where each sensor reports its complete observation to the fusion center (FC), and quantized-and-Coded DD (CDD), where each sensor first partitions the observation space and then reports to the FC a codeword. In this paper, we introduce Quantized-but-uncoded DD (QDD), where each sensor, after quantization, transmits a summarized value, instead of a codeword, to the FC. We show that QDD well adapts to the constraint of transmission power when compared to CDD, albeit with increased complexity in parameter selection. Moreover, we establish that, in the presence of independent observations, QDD upholds a necessary condition inherent in CDD. Specifically, the optimal sensor decision rules are the likelihood ratio quantizers (LRQ), irrelevant to the channel conditions. In the context of a single-sensor scenario involving binary decision at the sensor, we find that the optimal sensor rule in QDD is in general no longer ``channel blind", a feature presented in CDD. In addition, we compare these systems numerically under the same transmission power and bandwidth, while assuming additive white Gaussian noise (AWGN) in both sensing and reporting stages. Finally, we present some potential directions for future research.

Extract-Transform-Load for Video Streams

Social media, self-driving cars, and traffic cameras produce video streams at large scales and cheap cost. However, storing and querying video at such scales is prohibitively expensive. We propose to treat large-scale video analytics as a data warehousing problem: Video is a format that is easy to produce but needs to be transformed into an application-specific format that is easy to query. Analogously, we define the problem of Video Extract-Transform-Load (V-ETL). V-ETL systems need to reduce the cost of running a user-defined V-ETL job while also giving throughput guarantees to keep up with the rate at which data is produced. We find that no current system sufficiently fulfills both needs and therefore propose Skyscraper, a system tailored to V-ETL. Skyscraper can execute arbitrary video ingestion pipelines and adaptively tunes them to reduce cost at minimal or no quality degradation, e.g., by adjusting sampling rates and resolutions to the ingested content. Skyscraper can hereby be provisioned with cheap on-premises compute and uses a combination of buffering and cloud bursting to deal with peaks in workload caused by expensive processing configurations. In our experiments, we find that Skyscraper significantly reduces the cost of V-ETL ingestion compared to adaptions of current SOTA systems, while at the same time giving robustness guarantees that these systems are lacking.

SEED: Simple, Efficient, and Effective Data Management via Large Language Models

We introduce SEED, an LLM-centric system that allows users to easily create efficient, and effective data management applications. SEED comprises three main components: code generation, model generation, and augmented LLM query to address the challenges that LLM services are computationally and economically expensive and do not always work well on all cases for a given data management task. SEED addresses the expense challenge by localizing LLM computation as much as possible. This includes replacing most of LLM calls with local code, local models, and augmenting LLM queries with batching and data access tools, etc. To ensure effectiveness, SEED features a bunch of optimization techniques to enhance the localized solution and the LLM queries, including automatic code validation, code ensemble, model representatives selection, selective tool usages, etc. Moreover, with SEED users are able to easily construct a data management solution customized to their applications. It allows the users to configure each component and compose an execution pipeline in natural language. SEED then automatically compiles it into an executable program. We showcase the efficiency and effectiveness of SEED using diverse data management tasks such as data imputation, NL2SQL translation, etc., achieving state-of-the-art few-shot performance while significantly reducing the number of required LLM calls.

VerifAI: Verified Generative AI

Generative AI has made significant strides, yet concerns about the accuracy and reliability of its outputs continue to grow. Such inaccuracies can have serious consequences such as inaccurate decision-making, the spread of false information, privacy violations, legal liabilities, and more. Although efforts to address these risks are underway, including explainable AI and responsible AI practices such as transparency, privacy protection, bias mitigation, and social and environmental responsibility, misinformation caused by generative AI will remain a significant challenge. We propose that verifying the outputs of generative AI from a data management perspective is an emerging issue for generative AI. This involves analyzing the underlying data from multi-modal data lakes, including text files, tables, and knowledge graphs, and assessing its quality and consistency. By doing so, we can establish a stronger foundation for evaluating the outputs of generative AI models. Such an approach can ensure the correctness of generative AI, promote transparency, and enable decision-making with greater confidence. Our vision is to promote the development of verifiable generative AI and contribute to a more trustworthy and responsible use of AI.

Lingua Manga: A Generic Large Language Model Centric System for Data Curation

Data curation is a wide-ranging area which contains many critical but time-consuming data processing tasks. However, the diversity of such tasks makes it challenging to develop a general-purpose data curation system. To address this issue, we present Lingua Manga, a user-friendly and versatile system that utilizes pre-trained large language models. Lingua Manga offers automatic optimization for achieving high performance and label efficiency while facilitating flexible and rapid development. Through three example applications with distinct objectives and users of varying levels of technical proficiency, we demonstrate that Lingua Manga can effectively assist both skilled programmers and low-code or even no-code users in addressing data curation challenges.