1 citations · 1 across the 15 of their papers we have counts for
16 papers
ML Engineering Agents - A Data Management Perspective
Arnab Phani, Elias Strauss, Tim Schuster +1
Machine learning engineering (MLE) agents are emerging as a new paradigm for automating end-to-end ML pipeline development. Using large language models for code generation and pred…
Learning how to Forget: Fine-tuning for Long-Context Sparse Attention
Matthias Seeger, Zeyu Zhang, Vihang Patil +2
A lot of prior work addressed key-value (KV) cache selection and compression by sparse attention to enable long-context inference for transformer language models without excessive…
"Will This Data Break My Task?" - Interactive Synthesis of Task-Aware Data Unit Tests
Hao Chen, Arnab Phani, Sebastian Schelter
Data is a central resource for modern enterprises and institutions, and data errors propagating through data pipelines lead to serious impact in production. Therefore, data validat…
Beyond Scale and Generation: Understanding Language Model-based Entity Matching
Zeyu Zhang, Xue Li, Iacer Calixto +2
Entity matching identifies records that refer to the same real-world entity. Language models can be adapted to this task through bi-encoder, cross-encoder, and generative matcher a…
SemPiper: Interactive Code Synthesis for Semantic Operators in Machine Learning Pipelines
Olga Ovcharenko, Luciano Duarte, Sebastian Schelter
Machine learning (ML) pipelines require extensive data preparation, feature engineering, and integration across heterogeneous sources, making them tedious and error-prone to develo…
Be Fair! Can Machine Learning Engineering Agents Adhere to Fairness Constraints?
Anna Richter, Julia Stoyanovich, Sebastian Schelter
Machine learning engineering (MLE) agents promise to automate end-to-end ML pipeline development from raw data and natural language instructions, potentially making ML accessible t…
ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset
Luciano Duarte, Olga Ovcharenko, Sebastian Schelter
Multi-modal data management has emerged as a central research topic in the database community, spanning data integration, semantic query processing, and data quality assessment. De…
PrismaDV: Automated Task-Aware Data Unit Test Generation
Hao Chen, Arnab Phani, Sebastian Schelter
Data is a central resource for modern enterprises, and data validation is essential for ensuring the reliability of downstream applications. However, existing automated data unit t…
stratum: A System Infrastructure for Massive Agent-Centric ML Workloads
Arnab Phani, Elias Strauss, Sebastian Schelter
Recent advances in large language models (LLMs) transform how machine learning (ML) pipelines are developed and evaluated. LLMs enable a new type of workload, agentic pipeline sear…
Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based Batch Processing Framework
Chuangtao Ma, Zeyu Zhang, Arijit Khan +2
Large language models (LLMs) offer a compelling approach to entity matching (EM) in label-scarce settings, yet their matching quality is sensitive to records with ambiguous or spar…
SemPipes -- Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines
Olga Ovcharenko, Matthias Boehm, Sebastian Schelter
Real-world machine learning on tabular data relies on complex data preparation pipelines for prediction, data integration, augmentation, and debugging. Designing these pipelines re…
Towards Cross-Modal Error Detection with Tables and Images
Olga Ovcharenko, Sebastian Schelter
Ensuring data quality at scale remains a persistent challenge for large organizations. Despite recent advances, maintaining accurate and consistent data is still complex, especiall…
Towards a Real-World Aligned Benchmark for Unlearning in Recommender Systems
Pierre Lubitzsch, Olga Ovcharenko, Hao Chen +2
Modern recommender systems heavily leverage user interaction data to deliver personalized experiences. However, relying on personal data presents challenges in adhering to privacy…
AmbiGraph-Eval: Can LLMs Effectively Handle Ambiguous Graph Queries?
Yuchen Tian, Kaixin Li, Hao Chen +5
Large Language Models (LLMs) have recently demonstrated strong capabilities in translating natural language into database queries, especially when dealing with complex graph-struct…
scSSL-Bench: Benchmarking Self-Supervised Learning for Single-Cell Data
Olga Ovcharenko, Florian Barkmann, Philip Toma +4
Self-supervised learning (SSL) has proven to be a powerful approach for extracting biologically meaningful representations from single-cell data. To advance our understanding of SS…
AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model
Zeyu Zhang, Paul Groth, Iacer Calixto +1
Entity matching (EM) is the problem of determining whether two records refer to same real-world entity, which is crucial in data integration, e.g., for product catalogs or address…