No article text was recorded for this version.
symmetric loss functions
Version 1 of 145 papers72 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Memorization in Deep Neural Networks: Does the Loss Function matter?
- Blog: On Symmetric Losses for Learning from Corrupted Labels
- Blog: On Robustness of Neural Architecture Search Under Label Noise
- Blog: Robust Loss Functions under Label Noise for Deep Neural Networks
- Blog: Symmetric Graph Contrastive Learning against Noisy Views for Recommendation
- Blog: Learning with Noisy Labels
- Blog: Learning with Symmetric Label Noise: The Importance of Being Unhinged
- Blog: Joint Asymmetric Loss for Learning with Noisy Labels
- Blog: Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial
- Blog: Being Properly Improper
- Blog: Do We Really Need Gold Samples for Sample Weighting Under Label Noise?
- Blog: Making risk minimization tolerant to label noise
- Blog: Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation
- Blog: A Symmetric Loss Perspective of Reliable Machine Learning
- Blog: Learning from Noisy Complementary Labels with Robust Loss Functions
- Blog: On Symmetric Losses for Learning from Corrupted Labels
- Blog: Nrat: towards adversarial training with inherent label noise
- Blog: Learning Only from Relevant Keywords and Unlabeled Documents
- Blog: Robust Federated Learning with Noisy and Heterogeneous Clients
- Blog: Towards Theoretical Understanding of Weak Supervision for Information Retrieval
- Blog: Loss factorization, weakly supervised learning and label noise robustness
- Blog: Being Properly Improper
- Blog: Active Negative Loss Functions for Learning with Noisy Labels
- Blog: Learning Only from Relevant Keywords and Unlabeled Documents
- Blog: Optimized Gradient Clipping for Noisy Label Learning
- Blog: Symmetric Graph Contrastive Learning against Noisy Views for Recommendation
- Blog: Mean Field Theory in Deep Metric Learning
- Blog: Learning from Noisy Similar and Dissimilar Data
- Blog: Active Negative Loss: A Robust Framework for Learning with Noisy Labels
- Blog: An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions
- Blog: Not Just Object, But State: Compositional Incremental Learning without Forgetting
- Blog: Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
- Blog: Robust Classification with Noisy Labels Based on Posterior Maximization
- Blog: Robust Bayesian Optimization via Localized Online Conformal Prediction
- Blog: Learning with Noisy Labels
- Blog: An Inclusive Theoretical Framework of Robust Supervised Contrastive Loss against Label Noise
- Blog: Robust Imitation Learning from Noisy Demonstrations
- Blog: Deep Learning is Provably Robust to Symmetric Label Noise
- Blog: Symmetric Cross Entropy for Robust Learning With Noisy Labels
- Blog: BSL: Understanding and Improving Softmax Loss for Recommendation
- Blog: Analysis of Learning from Positive and Unlabeled Data
- Blog: $\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
- Blog: Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
- Blog: Exploring Loss Design Techniques For Decision Tree Robustness To Label Noise
- Blog: Asymmetric Loss Functions for Learning with Noisy Labels
History & citation
Current · Permanent link
- This direction split from Symmetric Loss Functions for Robust Label Noise Learning (96% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_symmetric_loss_functions_a8db9797,
title = {symmetric loss functions},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/symmetric-loss-functions/rdr_a8db979784034ed4be5dc8d143019658},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_symmetric_loss_functions_a8db9797_v1,
title = {symmetric loss functions},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/symmetric-loss-functions/rdr_a8db979784034ed4be5dc8d143019658/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}