Learning from Partial Labels

By Timothée Cour, Benjamin Sapp, B. Taskar. Journal of machine learning research, 2011

598 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/442f09ddb5bb7ba4e824c0795e37cad754967208

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Constrained Learning With Non-Convex Losses (2021, background): “Such constraints can also be used to incorporate prior knowledge, such as smoothness or sparsity [24]–[26], and tackle semi-supervised problems [27], [28].”
Bootstrapping Generators from Noisy Data (2018, background): “, 2002), object detection (Carbonetto et al., 2008; Cour et al., 2011), text classification (Andrews and Hofmann, 2004), image captioning (Wu et al.”
Large-Scale Object Classification Using Label Relation Graphs (2014, result): “By treating unobserved labels as latent variables, our approach also connects to prior work on learning from partial or incomplete labels [19,7,5].”
It ’ s in the bag : Stronger supervision for automated face labelling (2015, methodology): “This topic has received plenty of attention in the community and papers have investigated the problem under various assumptions on the available information [2, 3, 5, 4, 6, 8, 9, 12, 17, 18, 20, 22, 24].”
Degrees of supervision (2011, background): “The candidate pool always includes the correct label and it may also include an ambiguity set Cour et al. (2011).”
Neural Learning of One-of-Many Solutions for Combinatorial Problems in Structured Output Spaces (2020, background): “ may appear similar to the setting of 1oML, but are actually different from it. We ﬁrst discuss them brieﬂy. ‘Partial Label Learning’ (PLL) [Cabannes et al., 2020, Xu et al., 2019, Feng and An, 2019, Cour et al., 2011, Jin and Ghahramani, 2002] involves learning from the training data where, for eac”
Weakly supervised learning via statistical sufficiency (2016, background): “, 1997] and learning from label proportions [Kuck and de Freitas, 2005], or given in a candidate set which include the only correct one, as in partial labels or superset label learning [Cour et al., 2011; Liu and Dietterich, 2014].”
CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases (2016, background): “In the context of modeling noisy labels, our work is related to partial-label learning [42, 8, 37] and multi-label multi-instance learning [49], which deals with the problem where each training instance is associated with a set of noisy candidate labels (whereonly one is correct).”
Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study (2015, background): “• Partial label: It is a paradigm proposed in [71].”
A Review on Multi-Label Learning Algorithms (2014, background): “In the extreme case, only one label in the label set is valid and all the other labels in Y are false positive ones, and this setting has been recently termed as partial label learning [28].”
Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding (2016, methodology): “(8) CLPL [2]: uses a linear model to encourage large average scores for candidate types.”