Low-latency geo-distributed applications currently face the barrier of cross-site coordination for ensuring state consistency. Existing mixed-consistency models leverage the existence of strongly- and weakly-consistent operations in a given application, to avoid coordination whenever possible. However, existing approaches are rather pessimistic, coordinating more than is necessary. In this paper, we introduce Semi-Linearizability (SL): a consistency model that executes application operations with linearizability guarantees only when strictly necessary, avoiding over-coordination. Specifically, we propose novel operation semantics that can encode ordering relationships between application operations and map them to coordination primitives. Our proposed semantics can be used to reason over latent, asymmetric dependencies between different operations and optimize their execution. We show how SL enables a new class of safe, uncoordinated operations that previous models would otherwise execute under globally strict order, while offering substantial performance gains without violating application invariants. To demonstrate the advantages of SL, we implemented DeMon, a system that achieves four orders of magnitude lower latency on the most frequent operation in the widely used RUBiS benchmark compared to state-of-the-art systems.

Multiple works in data management research focus on automating the processes of data augmentation and feature discovery to save users from having to perform these tasks manually. Yet, this automation often leads to a disconnect with the users, as it fails to consider the specific needs and preferences of the actual end-users of data management systems for machine learning. To explore this issue further, we conducted 19 semi-structured, think-aloud use-case studies based on a scenario in which data specialists were tasked with augmenting a base table with additional features to train a machine learning model. In this paper, we share key insights into the practices of feature discovery on tabular data performed by real-world data specialists derived from our user study. Our research uncovered differences between the user assumptions reported in the literature and the actual practices, as well as some areas where literature and real-world practices align.

The advent of Large Language Models (LLMs) provides an opportunity to change the way queries are processed, moving beyond the constraints of conventional SQL-based database systems. However, using an LLM to answer a prediction query is still challenging, since an external ML model has to be employed and inference has to be performed in order to provide an answer. This paper introduces LLM-PQA, a novel tool that addresses prediction queries formulated in natural language. LLM-PQA is the first to combine the capabilities of LLMs and retrieval-augmented mechanism for the needs of prediction queries by integrating data lakes and model zoos. This integration provides users with access to a vast spectrum of heterogeneous data and diverse ML models, facilitating dynamic prediction query answering. In addition, LLM-PQA can dynamically train models on demand, based on specific query requirements, ensuring reliable and relevant results even when no pre-trained model in a model zoo, available for the task.

Given a set of pre-trained Machine Learning (ML) models, can we solve complex analytic tasks that make use of those models by formulating ML inference queries? Can we mitigate different tradeoffs, e.g., high accuracy, low execution costs and memory footprint, when optimizing the queries? In this work we present different multi-objective ML inference query optimization strategies, and compare them on their usability, applicability, and complexity. We formulate Mixed-Integer-Programming-based (MIP) optimizers for ML inference queries that makes use of different objectives to find Pareto-optimal inference query plans.