Research map / Learning theory and algorithms / Submodular and game algorithms
Data Summarization at Scale: A Two-Stage Submodular Approach
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Replacement-Streaming instead of Replacement-Greedy | VOC2012 image summarization · VOC2012 | objective value | No clear effect |
| Use Replacement-Streaming instead of Replacement-Greedy | VOC2012 image summarization · VOC2012 | running time: a full order of magnitude | Helped |
| Use Replacement-Streaming instead of Stream-Sum | VOC2012 image summarization · VOC2012 | objective value | Helped |
| Use Replacement-Streaming instead of Stream-Sum | VOC2012 image summarization · VOC2012 | running time | Helped |
| Increase epsilon up to 0.5 | Replacement-Streaming · VOC2012 | objective value: epsilon = 0.5 | No clear effect |
| Increase epsilon up to 0.5 | Replacement-Streaming · VOC2012 | running time: epsilon = 0.5 | Helped |
| Use Replacement-Distributed instead of Distributed-Greedy | ride-share optimization · Manhattan pickup regions | average customer-to-driver distance | Helped |
| Use Distributed-Fast instead of the other distributed algorithms | ride-share optimization · Manhattan pickup regions | running time | Helped |
| Use any of the three proposed summaries instead of a random summary | ride-share optimization on new regions · new regions drawn from the same distribution | cost | Helped |
Closest papers by meaning
- Submodular Span, with Applications to Conditional Data Summarization (AAAI 2021 · similarity 0.89)
- Learning Sparse Combinatorial Representations via Two-stage Submodular Maximization (ICML 2016 · similarity 0.89)
- Fast Constrained Submodular Maximization: Personalized Data Summarization (ICML 2016 · similarity 0.89)
- Noisy Submodular Maximization via Adaptive Sampling with Applications to Crowdsourced Image Collection Summarization (AAAI 2016 · similarity 0.88)
- FedSum: Data-Efficient Federated Learning Under Data Scarcity Scenario for Text Summarization (AAAI 2025 · similarity 0.84)
- Online Two-Stage Submodular Maximization (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.