Papers › When Optimizing f-divergence is Robust with Label Noise

When Optimizing f-divergence is Robust with Label Noise

7 Nov 2020ICLR 2021 1arXiv:2011.03687archive 2025-07-28

Jiaheng Wei, Yang Liu

We show when maximizing a properly defined f-divergence measure with respect to a classifier's predictions and the supervised labels is robust with label noise. Leveraging its variational form, we derive a nice decoupling property for a family of f-divergence measures when label noise presents, where the divergence is shown to be a linear combination of the variational difference defined on the clean distribution and a bias term introduced due to the noise. The above derivation helps us analyze the robustness of different f-divergence functions. With established robustness, this family of f-divergence functions arises as useful metrics for the problem of learning with noisy labels, which do not require the specification of the labels' noise rate. When they are possibly not robust, we propose fixes to make them so. In addition to the analytical results, we present thorough experimental evidence. Our code is available at https://github.com/UCSC-REAL/Robust-f-divergence-measures.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

weijiaheng/Robust-f-divergence-measures officialmentioned on GitHubpytorchSyntology: not harvested report
weijiaheng/Multi-class-Peer-Loss-functions mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates (arXiv:1910.03231; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Image ClassificationLearning with noisy labels

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Clothing1M Robust f-divergence Accuracy 73.09% #35 of 51 Archive leaderboard report
Learning with noisy labels CIFAR-100N F-div Accuracy (mean) 57.10 #18 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Aggregate F-div Accuracy (mean) 91.64 #14 of 26 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random1 F-div Accuracy (mean) 89.70 #17 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random2 F-div Accuracy (mean) 89.79 #14 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random3 F-div Accuracy (mean) 89.55 #15 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Worst F-div Accuracy (mean) 82.53 #18 of 25 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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