AnchorViz: Facilitating Classifier Error Discovery through Interactive Semantic Data Exploration
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
When building a classifier in interactive machine learning, human knowledge about the target class can be a powerful reference to make the classifier robust to unseen items. The main challenge lies in finding unlabeled items that can either help discover or refine concepts for which the current classifier has no corresponding features (i.e., it has feature blindness). Yet it is unrealistic to ask humans to come up with an exhaustive list of items, especially for rare concepts that are hard to recall. This paper presents AnchorViz, an interactive visualization that facilitates error discovery through semantic data exploration. By creating example-based anchors, users create a topology to spread data based on their similarity to the anchors and examine the inconsistencies between data points that are semantically related. The results from our user study show that AnchorViz helps users discover more prediction errors than stratified random and uncertainty sampling methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Power to the People: The Role of Humans in Interactive Machine Learning
Amershi, S., Cakmak, M., Knox, W. B., & Kulesza, T. (2014) · AI Magazine · doi:10.1609/aimag.v35i4.2513 · Cited by 1,084
Fails, J. A., & Olsen, D. R. (2003) · Proceedings of the 8th international conference on Intelligent user interfaces · doi:10.1145/604045.604056 · Cited by 633
Beat the Machine: Challenging Humans to Find a Predictive Model's “Unknown Unknowns”
Attenberg, J., Ipeirotis, P., & Provost, F. (2015) · Journal of Data and Information Quality · doi:10.1145/2700832 · Cited by 103 · cited 1×
“Active learning strategies are not suitable for finding unknown unknowns or feature blindness errors because they often rely on the model’s current training results, which cannot overcome the model’s blind spots [3, 13, 17].”
Background
Research works printed but not linked: 12
- 10.1057/ivs.2009.12 · DOI
- 10.1145/1835804.1835859 · DOI · Paper page
- 10.1016/S0022-5371(69)80069-1 · DOI · Paper page
- Inderjit S Dhillon and Dharmendra S Modha . 2001. Concept decompositions for large sparse text data using clustering. Machine learning 42, 1 ( 2001 ), 143--175. Inderjit S Dhillon and Dharmendra S Modha. 2001. Concept decompositions for large sparse text data using clustering. Machine learning 42, 1 (2001), 143--175.
- Inderjit Singh Dhillon and Dharmendra Shantilal Modha . 2003 . Concept decomposition using clustering. (May 6 2003) . US Patent 6 , 560 ,597. Inderjit Singh Dhillon and Dharmendra Shantilal Modha. 2003. Concept decomposition using clustering. (May 6 2003). US Patent 6,560,597.
- 10.5555/946251.947051 · doi:10.5555/946251.947051
- Camille Jandot , Patrice Simard , Max Chickering , David Grangier , and Jina Suh . 2016. Interactive Semantic Featuring for Text Classification. arXiv preprint arXiv:1606.07545 ( 2016 ). Camille Jandot, Patrice Simard, Max Chickering, David Grangier, and Jina Suh. 2016. Interactive Semantic Featuring for Text Classification. arXiv preprint arXiv:1606.07545 (2016). · arXiv
- 10.1145/2556288.2557238 · DOI · Paper page
- Himabindu Lakkaraju Ece Kamar Rich Caruana and Eric Horvitz. 2017. Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration. In AAAI. 2124--2132. Himabindu Lakkaraju Ece Kamar Rich Caruana and Eric Horvitz. 2017. Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration. In AAAI. 2124--2132. · DOI · Paper page
- 10.1111/j.1467-8659.2012.03108.x · DOI · Paper page
- Endel Tulving and others. 1972. Episodic and semantic memory . Organization of memory 1 ( 1972 ), 381--403. Endel Tulving and others. 1972. Episodic and semantic memory. Organization of memory 1 (1972), 381--403.
- 10.1006/ijhc.2001.0499 · DOI · Paper page
Cited by
Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need?
Holstein, K., Wortman Vaughan, J., Daumé, H., Dudik, M., & Wallach, H. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300830 · Cited by 777
“In addition, a growing body of research focuses on the design and development of programmer tools that can better support developers in debugging and effectively monitoring the predictive performance of complexML systems [5, 24, 63, 67, 85].”
BackgroundMethodA Conceptual Framework for Human–AI Hybrid Adaptivity in Education
Holstein, K., Aleven, V., & Rummel, N. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-52237-7_20 · Cited by 168
“As of yet, the question of how AIEd systems can be designed to effectively elicit and learn from such feedback remains underexplored (cf. [9, 10, 14, 23, 34, 54]).”
BackgroundThe Landscape and Gaps in Open Source Fairness Toolkits
Lee, M. S. A., & Singh, J. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445261 · Cited by 129
“Researchers have studied the design and development of tools to support developers in assessing and monitoring their models and systems [2, 7, 25], but none specifcally in fairness testing.”
BackgroundImproving Human-AI Collaboration With Descriptions of AI Behavior
Cabrera, Á. A., Perer, A., & Hong, J. I. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579612 · Cited by 87
“These include systems such as FairVis [10], a visual analytics system for discovering intersectional biases, AnchorViz [15], a visualization for semantically exploring datasets, and Slice Finder [18], a method for automatically surfacing subsets of data with large model loss.”
MethodSupporting Human-AI Collaboration in Auditing LLMs with LLMs
Rastogi, C., Ribeiro, M. T., King, N., Nori, H., & Amershi, S. (2023) · arXiv · doi:10.48550/arxiv.2304.09991 · Cited by 79
Metadata
- Authors
- Chen, N.-C., Suh, J., Verwey, J., Ramos, G., Drucker, S., & Simard, P.
- Venue
- 23rd International Conference on Intelligent User Interfaces
- Publisher
- ACM
- Published
- 2018-03-05
- Pages
- 269-280
- OpenAlex
- W2789415069
- Cited by
- 39
- References
- 3
- FWCI
- 1.69
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: AnchorViz: Facilitating Classifier Error Discovery through Interactive Semantic Data Exploration. https://app.cochat.ai/papers/10.1145/3172944.3172950
- The paper
- Chen, N.-C., Suh, J., Verwey, J., Ramos, G., Drucker, S., & Simard, P. (2018). AnchorViz: Facilitating Classifier Error Discovery through Interactive Semantic Data Exploration. 23rd International Conference on Intelligent User Interfaces. https://doi.org/10.1145/3172944.3172950
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.