In this paper, we propose Multi-Modal Databases (MMDBs), which is a new class of database systems that can seamlessly query text and tables using SQL. To enable seamless querying of textual data using SQL in an MMDB, we propose to extend relational databases with so-called multi-modal operators (MMOps) which are based on the advances of recent large language models such as GPT-3. The main idea of MMOps is that they allow text collections to be treated as tables without the need to manually transform the data. As we show in our evaluation, our MMDB prototype can not only outperform state-of-the-art approaches such as text-to-table in terms of accuracy and performance but it also requires significantly less training data to fine-tune the model for an unseen text collection.

Neural retrieval models (NRMs) have been shown to outperform their statistical counterparts owing to their ability to capture semantic meaning via dense document representations. These models, however, suffer from poor interpretability as they do not rely on explicit term matching. As a form of local per-query explanations, we introduce the notion of equivalent queries that are generated by maximizing the similarity between the NRM's results and the result set of a sparse retrieval system with the equivalent query. We then compare this approach with existing methods such as RM3-based query expansion and contrast differences in retrieval effectiveness and in the terms generated by each approach.

Derivative Free Optimization (DFO) is attractive when the objective function's derivatives are not available and evaluations are costly. Moreover, if the function evaluations are noisy, then approximating gradients by finite differences is difficult. This paper gives quantitative lower bounds on the performance of DFO with noisy function evaluations, exposing a fundamental and unavoidable gap between optimization performance based on noisy evaluations versus noisy gradients. This challenges the conventional wisdom that the method of finite differences is comparable to a stochastic gradient. However, there are situations in which DFO is unavoidable, and for such situations we propose a new DFO algorithm that is proved to be near optimal for the class of strongly convex objective functions.

There is an increasing adoption of machine learning for encoding data into vectors to serve online recommendation and search use cases. As a result, recent data management systems propose augmenting query processing with online vector similarity search. In this work, we explore vector similarity search in the context of Knowledge Graphs (KGs). Motivated by the tasks of finding related KG queries and entities for past KG query workloads, we focus on hybrid vector similarity search (hybrid queries for short) where part of the query corresponds to vector similarity search and part of the query corresponds to predicates over relational attributes associated with the underlying data vectors. For example, given past KG queries for a song entity, we want to construct new queries for new song entities whose vector representations are close to the vector representation of the entity in the past KG query. But entities in a KG also have non-vector attributes such as a song associated with an artist, a genre, and a release date. Therefore, suggested entities must also satisfy query predicates over non-vector attributes beyond a vector-based similarity predicate. While these tasks are central to KGs, our contributions are generally applicable to hybrid queries. In contrast to prior works that optimize online queries, we focus on enabling efficient batch processing of past hybrid query workloads. We present our system, HQI, for high-throughput batch processing of hybrid queries. We introduce a workload-aware vector data partitioning scheme to tailor the vector index layout to the given workload and describe a multi-query optimization technique to reduce the overhead of vector similarity computations. We evaluate our methods on industrial workloads and demonstrate that HQI yields a 31x improvement in throughput for finding related KG queries compared to existing hybrid query processing approaches.

A widely used interpretation by example We design, implement, and evaluate DeepEverest, a system for the query is, "find the top-inputs that produce the highest activation efficient execution of interpretation by example queries over the values for an individual neuron or a group of neurons" [12, 14, 21, activation values of a deep neural network. DeepEverest consists 33, 50, 57, 58, 61]. Another common query is, "for any input, find of an efficient indexing technique and a query execution algorithm the k-nearest neighbors in the dataset using the activation values of a with various optimizations. We prove that the proposed query group of neurons based on the proximity in the latent space defined execution algorithm is instance optimal.

In recent years, machine learning-based cardinality estimation methods are replacing traditional methods. This change is expected to contribute to one of the most important applications of cardinality estimation, the query optimizer, to speed up query processing. However, none of the existing methods do not precisely estimate cardinalities when relational schemas consist of many tables with strong correlations between tables/attributes. This paper describes that multiple density estimators can be combined to effectively target the cardinality estimation of data with large and complex schemas having strong correlations. We propose Scardina, a new join cardinality estimation method using multiple partitioned models based on the schema structure.

Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of previously seen data, which increases memory costs and may violate data privacy. Recently, the emergence of large-scale pre-trained vision transformer models has enabled prompting approaches as an alternative to data-rehearsal. These approaches rely on a key-query mechanism to generate prompts and have been found to be highly resistant to catastrophic forgetting in the well-established rehearsal-free continual learning setting. However, the key mechanism of these methods is not trained end-to-end with the task sequence. Our experiments show that this leads to a reduction in their plasticity, hence sacrificing new task accuracy, and inability to benefit from expanded parameter capacity. We instead propose to learn a set of prompt components which are assembled with input-conditioned weights to produce input-conditioned prompts, resulting in a novel attention-based end-to-end key-query scheme. Our experiments show that we outperform the current SOTA method DualPrompt on established benchmarks by as much as 4.5% in average final accuracy. We also outperform the state of art by as much as 4.4% accuracy on a continual learning benchmark which contains both class-incremental and domain-incremental task shifts, corresponding to many practical settings. Our code is available at https://github.com/GT-RIPL/CODA-Prompt

Vanilla graph databases are pretty much everywhere thanks to the ever-growing graphs in production, flexible graph data models, and expressive query languages. Query engines assume that graphs in classical graph DBs are complete. Under the completeness assumption, we can build indexes, store the graphs in a variety of read/write-optimized formats and expect the DB would return what is there. But this assumption does not often hold in practice (we'd say, doesn't hold way too often). If we look at some prominent knowledge graphs (KGs): in Freebase, 93.8% of people have no place of birth and 78.5% have no nationality, about 68% of people do not have any profession, while in Wikidata, about 50% of artists have no date of birth, and only 0.4% of known buildings have information about height.

Link Traversal-based Query Processing (ltqp), in which a sparql query is evaluated over a web of documents rather than a single dataset, is often seen as a theoretically interesting yet impractical technique. However, in a time where the hypercentralization of data has increasingly come under scrutiny, a decentralized Web of Data with a simple document-based interface is appealing, as it enables data publishers to control their data and access rights. While ltqp allows evaluating complex queries over such webs, it suffers from performance issues (due to the high number of documents containing data) as well as information quality concerns (due to the many sources providing such documents). In existing ltqp approaches, the burden of finding sources to query is entirely in the hands of the data consumer. In this paper, we argue that to solve these issues, data publishers should also be able to suggest sources of interest and guide the data consumer towards relevant and trustworthy data. We introduce a theoretical framework that enables such guided link traversal and study its properties. We illustrate with a theoretic example that this can improve query results and reduce the number of network requests. We evaluate our proposal experimentally on a virtual linked web with specifications and indeed observe that not just the data quality but also the efficiency of querying improves.

Being able to efficiently retrieve the required building information is critical for construction project stakeholders to carry out their engineering and management activities. Natural language interface (NLI) systems are emerging as a time and cost-effective way to query Building Information Models (BIMs). However, the existing methods cannot logically combine different constraints to perform fine-grained queries, dampening the usability of natural language (NL)-based BIM queries. This paper presents a novel ontology-aided semantic parser to automatically map natural language queries (NLQs) that contain different attribute and relational constraints into computer-readable codes for querying complex BIM models. First, a modular ontology was developed to represent NL expressions of Industry Foundation Classes (IFC) concepts and relationships, and was then populated with entities from target BIM models to assimilate project-specific information. Hereafter, the ontology-aided semantic parser progressively extracts concepts, relationships, and value restrictions from NLQs to fully identify constraint conditions, resulting in standard SPARQL queries with reasoning rules to successfully retrieve IFC-based BIM models. The approach was evaluated based on 225 NLQs collected from BIM users, with a 91% accuracy rate. Finally, a case study about the design-checking of a real-world residential building demonstrates the practical value of the proposed approach in the construction industry.