On the Consistency of Multi-Label Learning

By Wei Gao, Zhi-Hua Zhou. 2011

155 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Molecular Biology, Evaluation & Benchmarks

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 Molecular Biology

In Evaluation & Benchmarks

Citations in the corpus

On Structured Prediction Theory with Calibrated Convex Surrogate Losses (2017, background): “Gao & Zhou [18] focus on multi-label classification.”
Convex Calibrated Surrogates for Low-Rank Loss Matrices with Applications to Subset Ranking Losses (2013, background): “As noted earlier, various loss functions are used in practice, and there has been much interest in understanding questions of consistency and calibration for these losses in recent years [9–15, 17].”
Large-Scale Multi-label Text Classification - Revisiting Neural Networks (2013, background): “k Loss Recently, it has been claimed that none of convex loss functions including BP-MLL’s loss function (Equation 3) is consistent with respect to rank loss which is non-convex and has discontinuity [2, 9]. Furthermore, univariate surrogate loss functions such as log loss are rather consistent with”
A Consistent Regularization Approach for Structured Prediction (2016, background): “Indeed, in the last few years, an effort has been made to analyze specific structured problems, such as multiclass classification [5], multi-labeling [6], ranking [7] or quantile estimation [8].”
A Review on Multi-Label Learning Algorithms (2014, background): “By focusing on ranking loss, it is disclosed that none pairwise convex surrogate loss defined on label pairs is consistent with the ranking loss and some recent multilabel approach [40] is inconsistent even for deterministic multi-label learning [32].”
Convex Calibration Dimension for Multiclass Loss Matrices (2014, methodology): “…in understanding consistency properties of surrogate risk minimization algorithms for various learning problems, such as binary clas-siﬁcation, multiclass 0-1 classiﬁcation, and various forms of ranking and multi-label prediction problems [18, 14, 34, 26, 2, 33, 28, 27, 8, 31, 10, 23, 4, 12, 15].”
Binary relevance for multi-label learning: an overview (2018, background): “Therefore, the actual multi-label metric being optimized depends on the binary loss, which is minimized by the binary learning algorithmB [46,47]; • Finally, binary relevance can be easily adapted to learn from multi-label examples with missing labels, where the labeling information for training exa”
Cross-Entropy Loss Functions: Theoretical Analysis and Applications (2023, unknown): “…& Agarwal, 2016; Finocchiaro et al., 2019; Frongillo & Waggoner, 2021; Finocchiaro et al., 2022; Wang & Scott, 2023), multi-label classification (Gao & Zhou, 2011; Dembczynski et al., 2012; Zhang et al., 2020b), learning with rejection (Cortes et al., 2016b;a; Ramaswamy et al., 2015; Cao et…”
The Emerging Trends of Multi-Label Learning (2020, background): “For example, [169] studies two well-known multi-label loss functions: ranking loss and hamming loss.”