AHAlon Halevy

Alon Halevy

*This is an algorithmically generated author record based on publicly available information.

Alon Halevy has a total of 54 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models: [Experiments & Analysis]

    by Yeounoh Chung, Rushabh Desai, Jian He, Yu Xiao, Thibaud Hottelier, Yves-Laurent Kom Samo, Pushkar Khadilkar, Xianshun Chen, Sam Idicula, Fatma Ozcan, et al.

    Several data warehouse and database providers have recently introduced extensions to SQL called AI Queries, enabling users to specify functions and conditions in SQL that are evaluated by LLMs, thereby broadening significantly the kinds of queries one can express over the combination of structured and unstructured data. LLMs offer remarkable semantic reasoning capabilities, making them an essential tool for complex and nuanced queries that blend structured and unstructured data. While extremely powerful, these AI queries can become prohibitively costly when invoked thousands of times. This paper provides an extensive evaluation of a recent AI query approximation approach that enables low cost analytics and database applications to benefit from AI queries. The approach delivers >100x cost and latency reduction for the semantic filter (AI.IF) operator and also important gains for semantic ranking (AI.RANK). The cost and performance gains come from utilizing cheap and accurate proxy models over embedding vectors. We show that despite the massive gains in latency and cost, these proxy models preserve accuracy and occasionally improve accuracy across various benchmark datasets, including the extended Amazon reviews benchmark that has 10M rows. We present an OLAP-friendly architecture within Google BigQuery for this approach for purely online (ad hoc) queries, and a low-latency HTAP database-friendly architecture in AlloyDB that could further improve the latency by moving the proxy model training offline. We present techniques that accelerate the proxy model training.


  • Top Cited Papers
    Open Access

    Building Human Values into Recommender Systems: An Interdisciplinary Synthesis

    by Jonathan Stray, Alon Halevy, Parisa Assar, Dylan Hadfield-Menell, Craig Boutilier, Amar Ashar, Chloe Bakalar, Lex Beattie, Michael Ekstrand, Claire Leibowicz, et al.

    Recommender systems are the algorithms which select, filter, and personalize content across many of the world's largest platforms and apps. As such, their positive and negative effects on individuals and on societies have been extensively theorized and studied. Our overarching question is how to ensure that recommender systems enact the values of the individuals and societies that they serve. Addressing this question in a principled fashion requires technical knowledge of recommender design and operation, and also critically depends on insights from diverse fields including social science, ethics, economics, psychology, policy, and law. This article is a multidisciplinary effort to synthesize theory and practice from different perspectives, with the goal of providing a shared language, articulating current design approaches, and identifying open problems. We collect a set of values that seem most relevant to recommender systems operating across different domains, and then examine them from the perspectives of current industry practice, measurement, product design, and policy approaches. Important open problems include multi-stakeholder processes for defining values and resolving trade-offs, better values-driven measurements, recommender controls that people use, non-behavioral algorithmic feedback, optimization for long-term outcomes, causal inference of recommender effects, academic-industry research collaborations, and interdisciplinary policy-making.


  • Open Access

    DiaryHelper: Exploring the Use of an Automatic Contextual Information Recording Agent for Elicitation Diary Study

    by Junze Li, Changyang He, Jiaxiong Hu, Boyang Jia, Alon Y Halevy, Xiaojuan Ma

    Elicitation diary studies, a type of qualitative, longitudinal research method, involve participants to self-report aspects of events of interest at their occurrences as memory cues for providing details and insights during post-study interviews. However, due to time constraints and lack of motivation, participants’ diary entries may be vague or incomplete, impairing their later recall. To address this challenge, we designed an automatic contextual information recording agent, DiaryHelper, based on the theory of episodic memory. DiaryHelper can predict five dimensions of contextual information and confirm with participants. We evaluated the use of DiaryHelper in both the recording period and the elicitation interview through a within-subject study (N=12) over a period of two weeks. Our results demonstrated that DiaryHelper can assist participants in capturing abundant and accurate contextual information without significant burden, leading to a more detailed recall of recorded events and providing greater insights.


  • Open Access

    Multimodal Neural Databases

    by Giovanni Trappolini, Andrea Santilli, Emanuele Rodolà, Alon Halevy, Fabrizio Silvestri


  • Open Access

    Personal Data for Personal Use: Vision or Reality?

    by Xin Luna Dong, Bo Li, Julia Stoyanovich, Anthony Kum Hoe Tung, Gerhard Weikum, Alon Halevy, Wang-Chiew Tan

    The vision of collecting all of one's personal information into one searchable database has been around at least since Vannevar Bush's 1945 paper on the Memex System [2]. In the late 1990's, Gordon Bell and his colleagues at Microsoft Research built MyLifeBits [1, 6], which was the first serious attempt to build such a database. Since then, there has been continued interest in our community to build personal information management systems [3-5, 7, 8, 10]. Recently, the Solid Project proposes a more radical approach to personal information, arguing that all of one's data should reside in their own data pod, and applications should be redesigned to fetch data from the pod [9].


  • Open Access

    Discovering Subsumption Relationships for Web-Based Ontologies

    by Dana Movshovitz-Attias, Steven Euijong Whang, Natalya Noy, Alon Halevy

    As search engines are becoming smarter at interpreting user queries and providing meaningful responses, they rely on ontologies to understand the meaning of entities. Creating ontologies manually is a laborious process, and resulting ontologies may not reflect the way users think about the world, as many concepts used in queries are noisy, and not easily amenable to formal modeling. There has been considerable effort in generating ontologies from Web text and query streams, which may be more reflective of how users query and write content. In this paper, we describe the LATTE system that automatically generates a subconcept--superconcept hierarchy, which is critical for using ontologies to answer queries. LATTE combines signals based on word-vector representations of concepts and dependency parse trees; however, LATTE derives most of its power from an ontology of attributes extracted from the Web that indicates the aspects of concepts that users find important. LATTE achieves an F1 score of 74%, which is comparable to expert agreement on a similar task. We additionally demonstrate the usefulness of LATTE in detecting high quality concepts from an existing resource of IsA links.


  • Data Matching

    by AnHai Doan, Alon Halevy, Zachary Ives

  • Open Access

    Mining structures for semantics

    by Xin Dong, Jayant Madhavan, Alon Halevy

    Online data is available in two avors: unstructured data that resides as free text in HTML pages, and structured data that resides in databases and knowledge bases. Unstructured data is easily accessed as human-readable text on a browser, while structured data is hidden behind web query interfaces (web forms), web services, and custom database APIs. Access to this data, popularly referred to as the hidden web, entails submitting correctly completed web forms or writing code to access web services using protocols such as SOAP.