Papers › sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification

sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification

24 Aug 2021arXiv:2108.10566archive 2025-07-28

Gabriel Bénédict, Vincent Koops, Daan Odijk, Maarten de Rijke

Multiclass multilabel classification is the task of attributing multiple labels to examples via predictions. Current models formulate a reduction of the multilabel setting into either multiple binary classifications or multiclass classification, allowing for the use of existing loss functions (sigmoid, cross-entropy, logistic, etc.). Multilabel classification reductions do not accommodate for the prediction of varying numbers of labels per example and the underlying losses are distant estimates of the performance metrics. We propose a loss function, sigmoidF1, which is an approximation of the F1 score that (1) is smooth and tractable for stochastic gradient descent, (2) naturally approximates a multilabel metric, and (3) estimates label propensities and label counts. We show that any confusion matrix metric can be formulated with a smooth surrogate. We evaluate the proposed loss function on text and image datasets, and with a variety of metrics, to account for the complexity of multilabel classification evaluation. sigmoidF1 outperforms other loss functions on one text and two image datasets and several metrics. These results show the effectiveness of using inference-time metrics as loss functions for non-trivial classification problems like multilabel classification.

PaperPDFCode

Code

gabriben/metrics-as-losses officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAdamAttentionAttention DropoutAverage PoolingBERTBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDistilBERTDropoutInverted Residual BlockLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPointwise ConvolutionResidual ConnectionSoftmaxWeight DecayWordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections