(Almost) No Label No Cry

By Giorgio Patrini, Richard Nock, Tibério S. Caetano, Paul Rivera. 2014

122 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption (2017, background): “We assume without loss of generality that ‖θ∗‖2 6= 0, a property guaranteed to hold if the mean operator is not the null vector [Patrini et al., 2014].”
Fast Learning from Distributed Datasets without Entity Matching (2016, background): “However, as argued in Section 6, if at least one peer has classes than all peers can get their labels as well without entity resolution, by the use of algorithms that learn with label proportions [Patrini et al., 2014; Quadrianto et al., 2009].”
Entity Resolution and Federated Learning get a Federated Resolution (2018, background): “5) We remark a difference with Theorem 8: the bound also depends on δS , and so on the norm of a sufficient statistics for the class, the mean operator [23].”
Loss factorization, weakly supervised learning and label noise robustness (2016, methodology): “We translate this property for classiﬁcation with erm , by transferring the ideas of suﬃciency and factorization to a wide set of losses including the ones of [Patrini et al., 2014].”
Rademacher Observations, Private Data, and Boosting (2015, background): “When σ = y is the vector of classes, πσ = mμS is m times the mean operator, a minimal sufficient statistics for the class (Quadrianto et al., 2009; Patrini et al., 2014).”
Classification without labels: learning from mixed samples in high energy physics (2017, background): “[34] to distinguish jets originating from quarks from those originating from gluons using only class proportions during training; this paradigm is known as learning from label proportions (LLP) [35, 36].”
Who Supported Obama in 2012?: Ecological Inference through Distribution Regression (2015, background): “A related line of work, termed“learning from label propor-tions” by some authors [24, 15, 30, 21], has the individual-level goal in mind, and aims to build a classiﬁer for individual instances based only on group level label proportions.”
From Group to Individual Labels Using Deep Features (2015, background): “Patrini et. al [25] developed theoretical results that show that a mean operator on the group labels can provide a minimally suﬃcient statistic for many proper cost functions deﬁned on labels of instances.”