AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration

Himabindu Lakkaraju, Ece Kamar, Rich Caruana, Eric Horvitz

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 148 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
Use DSP partitions instead of k-means partitions based on features, confidence scores, or bothUnknown-unknown discovery · Sentiment Snippets, Subjectivity, Amazon Reviews, Image Dataentropy of unknown-unknown distribution across partitionsImproved
Jointly partition using features and confidence scores rather than only features or only confidence scores (ablation)DSP · Sentiment Snippets, Subjectivity, Amazon Reviews, Image Dataentropy of unknown-unknown distribution across partitionsImproved
Use DSP instead of random partitioningUnknown-unknown discovery · Sentiment Snippets, Subjectivity, Amazon Reviews, Image Dataentropy of unknown-unknown distribution across partitions: 32-37% lowerImproved
Use UUB instead of random, greedy, epsilon-greedy, UCB, UCB_f, sliding-window, or discounted UCB policiesDSP partitions · Image Datacumulative regretImproved
Use UUB instead of the compared bandit policiesDSP partitions · Sentiment Snippets and Subjectivitycumulative regretImproved
Use UUB instead of discounted UCB with discounting factor 0.5DSP partitions · Amazon Reviewscumulative regretHurt
Use the complete DSP + UUB pipeline instead of random sampling, least-average-similarity, least-maximum-similarity, or most-uncertain samplingUnknown-unknown discovery · Image Datacumulative regretImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy