BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Information Systems Group - ECPv6.4.0.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://isg.ics.uci.edu
X-WR-CALDESC:Events for Information Systems Group
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250110T130000
DTEND;TZID=America/Los_Angeles:20250110T140000
DTSTAMP:20260430T183004
CREATED:20250211T004808Z
LAST-MODIFIED:20250211T004808Z
UID:2160-1736514000-1736517600@isg.ics.uci.edu
SUMMARY:Shengquan Ni: IcedTea: Efficient and Responsive Time-Travel Debugging in Dataflow Systems
DESCRIPTION:Abstract: As data analytics grow in popularity\, the increasing volume of data and complexity of jobs require users to wait longer to see results\, hindering productivity and causing frustration. To address this\, we developed an actor-based data processing engine optimized for pipelined execution\, featuring a flexible interface for defining control messages. This enables users to seamlessly customize and manage interactions during execution.\nWhile interactive systems help users identify incorrect behavior earlier\, the pipelined and distributed nature of execution often leads to non-deterministic behavior\, making it difficult to pinpoint the root cause of bugs. To tackle this\, we created IcedTea\, a time-travel debugger with tuple-based step semantics. IcedTea enables lightweight recording of execution\, allowing users to roll back to previous states and step forward to investigate issues effectively.\nAs data jobs increasingly operate in cloud environments\, adapting the system to the cloud is crucial. Challenges such as resource isolation and fault tolerance must be addressed to ensure security and reliability in distributed systems.\nIn this talk\, I will focus on IcedTea\, a time-travel debugger that allows users to record a pipelined distributed workflow execution and jump back to specific points to replay the execution step-by-step. Our evaluation demonstrates that IcedTea effectively helps identify state-related bugs with minimal overhead added to the original execution.
URL:https://isg.ics.uci.edu/event/shengquan-ni-icedtea-efficient-and-responsive-time-travel-debugging-in-dataflow-systems/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250117T130000
DTEND;TZID=America/Los_Angeles:20250117T140000
DTSTAMP:20260430T183004
CREATED:20241008T012400Z
LAST-MODIFIED:20250211T005019Z
UID:2114-1737118800-1737122400@isg.ics.uci.edu
SUMMARY:Abhishek Singh: LogPoseDB: Transaction Handoff and Agreement in Edge-Cloud Systems
DESCRIPTION:Abstract: Emerging IoT and edge applications demand fast response times that cannot be achieved by faraway cloud datacenters. This motivates building edge-cloud systems where nodes on the edge can participate in the processing and storage of data. However\, building an edge-cloud transaction processing system faces two main challenges: (1) Inefficient transaction execution due to low concurrency arising from long  Round Trip Times between Edge and Cloud\, (2)The absence of a dedicated edge nodes infrastructure\, and (2) edge nodes may be untrusted.\nWe propose LogPoseDB\, an edge-cloud database that spans both edge and cloud nodes. LogPoseDB aims to overcome the challenges above. LogPoseDB proposes dynamic state detachment\, where the state storage and processing is treated as a disjoint resource between the cloud and the edge. LogPoseDB’s transaction processing protocol ensures fast response by avoiding wide-area coordination with the cloud or other faraway edge nodes. This is done by leveraging data locality of detached state and by methods that build on the areas of transaction chopping and commutativity.\nLogPoseDB does not require any dedicated edge infrastructure. Rather\, clients may utilize their edge nodes—if desired—to perform the processing and storage of their data while they need it. (Other clients can still process their data on cloud nodes.)  To address the trust challenges\, we propose a byzantine fault-tolerant (BFT) protocol that targets edge nodes. LogPoseDB’s BFT replication protocol proposes the principle of  remote lazy trust that enables efficient BFT edge coordination by utilizing a remote trusted node asynchronously. \nBio: Abhishek is a PhD Candidate supervised by Prof. Faisal Nawab. His research includes building data management and transaction processing systems for the emerging Edge-Cloud infrastructure.
URL:https://isg.ics.uci.edu/event/abhishek-singh-talk/
LOCATION:DBH 3011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250124T110000
DTEND;TZID=America/Los_Angeles:20250124T120000
DTSTAMP:20260430T183004
CREATED:20250211T005142Z
LAST-MODIFIED:20250211T005142Z
UID:2163-1737716400-1737720000@isg.ics.uci.edu
SUMMARY:Xiaodong Zhang (The Ohio State University): Data Management: Interactions with Computer Architecture and Systems
DESCRIPTION:Abstract:  We have entered a data-centric computing era\, characterized by the coexistence of diverse parallel and specialized hardware accelerators along with general-purpose processors. In this ecosystem\, minimizing data movement has become a critical priority for the design of both systems and applications. Over the years\, the CPU-centric ecosystem has evolved into a one-size-fits-all environment\, supporting a wide variety of applications. However\, its efficiency in performance\, computational power\, and energy consumption has steadily declined\, making the general-purpose computing model increasingly unsustainable for the rapidly growing demand of data analytics and machine learning applications. In this presentation\, I will explore the constraints and obstacles inherent in our current computing ecosystem. I will also provide case studies to support the evolution of computer hardware and software for high-performance data processing\, featuring advanced hardware components such as GPUs\, RDMA\, and other relevant technologies. All associated algorithms and software implementations are open source\, with some having been integrated into production systems. The system infrastructure transition for data-centric workloads also challenges our college computer science education. In this context\, I will briefly introduce a new textbook of mine\, which shares the same title of this presentation\, and was published by Cambridge University Press last year. \nBio: Xiaodong Zhang is a University Distinguished Scholar and the Robert M. Critchfield Professor in Engineering at the Ohio State University. His research interests focus on data management in computer and distributed systems. Driven by a commitment to translate his academic research solutions into cutting-edge technology\, he has made continuous efforts in advancing the design and implementation of several major production systems. He was recognized by the 2020 ACM Microarchitecture Test of Time Award for his contributions on memory architecture design and the 2024 VLDB Test of Time Award for an initial development of open-source spatial data processing systems on large-scale clusters. He received his Ph.D. in Computer Science from University of Colorado at Boulder\, where he was honored with a Distinguished Engineering Alumni Award in 2011. He received the Education Leadership Award from the Lutron Foundation for chairing the Department of Computer Science and Engineering at Ohio State from 2006 to 2018. He is a Fellow of the ACM\, and a Fellow of the IEEE.
URL:https://isg.ics.uci.edu/event/xiaodong-zhang-the-ohio-state-university-data-management-interactions-with-computer-architecture-and-systems/
LOCATION:DBH 6011
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20250131T130000
DTEND;TZID=America/Los_Angeles:20250131T140000
DTSTAMP:20260430T183004
CREATED:20250211T005308Z
LAST-MODIFIED:20250211T005308Z
UID:2165-1738328400-1738332000@isg.ics.uci.edu
SUMMARY:Yicong Huang: Building Data Systems to Broaden the Access of Data Science\, AI\, and ML
DESCRIPTION:Abstract \nIn an era where data-driven decision-making shapes industries\, governments\, and everyday life\, the ability to leverage data science has become an essential skill. Modern data science tools—encompassing data collection\, analysis\, and advanced techniques such as artificial intelligence (AI)\, machine learning (ML)\, and large language models (LLMs)—play a critical role across diverse fields. However\, many of these tools rely heavily on programming expertise\, which limits their accessibility to a broader audience. In this talk\, I will discuss my work on Texera\, an open-source system designed to make data science\, AI\, and ML accessible to everyone. Texera features a low-code and even no-code workflow interface\, enabling users of varying technical backgrounds to engage in data science. It emphasizes cloud-based collaboration for data science\, enabling multiple users to seamlessly work on the same shared execution\, much like the collaborative experiences offered by Google Docs and Overleaf. I will discuss the design choices behind our actor-based parallel engine for executing data science workflows. I will also highlight my works on the system’s innovative features for interacting with data workflow executions\, focusing on debugging capabilities that improve transparency and enhance usability. To conclude\, I will outline future research directions aimed at developing a comprehensive ecosystem that integrates advanced interfaces and intelligent systems\, enhancing accessibility\, efficiency\, and user empowerment in data science. \nBio \nYicong Huang is a final-year Ph.D. candidate from the Information Systems Group (ISG)\, Computer Science Department\, University of California\, Irvine.  Under the guidance of Dr. Chen Li\, his research focuses on big data management\, data-processing systems\, and machine learning systems. Yicong has made significant contributions in the Texera project. He has published in top-tier database venues such as VLDB\, SIGMOD and ICDE. His interdisciplinary reach spans venues like TOCHI\, PNAS Nexus\, JAMIA\, AMIA\, and PloS ONE. Yicong completed research internships at Bytedance\, VISA\, and Observe\, and contributed to patents and papers. His research earned a Best Demo Runner-Up Award at SIGMOD 2024. He received honors such as the 2024 Graduate Dean’s Dissertation Fellowship and the 2023 Public Impact Fellowship from UCI. For more information about his work\, please visit https://yicong-huang.github.io.
URL:https://isg.ics.uci.edu/event/yicong-huang-building-data-systems-to-broaden-the-access-of-data-science-ai-and-ml/
LOCATION:DBH 3011
END:VEVENT
END:VCALENDAR