Distributional Loss for Robust Classification

• URL: http://arxiv.org/abs/2606.13223v1
• Date: Thu, 11 Jun 2026 11:38:37 GMT
• Title: Distributional Loss for Robust Classification
• Abstract summary: This paper proposes a novel loss concept for supervised classification tasks.<n>Rather than enforcing a direct mapping from each input sample to a single assigned label, we define an optimization objective over all classifier outputs as a bimodal Gaussian distribution.<n> Experimental results demonstrate consistent improvements in robustness, with particularly pronounced gains in low-data regimes, while requiring only minimal modifications to standard training pipelines.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This paper proposes a novel loss concept for supervised classification tasks. Rather than enforcing a direct mapping from each input sample to a single assigned label, we define an optimization objective over all classifier outputs as a bimodal Gaussian distribution. This softer target formulation implicitly captures class ambiguity, mitigates overfitting, and encourages the learning of more robust decision boundaries, all without requiring additional label information. Experimental results demonstrate consistent improvements in robustness, with particularly pronounced gains in low-data regimes, while requiring only minimal modifications to standard training pipelines.

Related papers

• Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation [22.474866164542302]
  UDA approaches commonly assume that source and target domains share the same labels space. This paper considers the more challenging Source-Free Open-set Domain Adaptation (SF-OSDA) setting. We propose a novel approach for SF-OSDA that exploits the granularity of target-private categories by segregating their samples into multiple unknown classes.
  arXiv  Detail & Related papers  (2024-04-16T13:52:00Z)
• Virtual Category Learning: A Semi-Supervised Learning Method for Dense Prediction with Extremely Limited Labels [63.16824565919966]
  This paper proposes to use confusing samples proactively without label correction. A Virtual Category (VC) is assigned to each confusing sample in such a way that it can safely contribute to the model optimisation. Our intriguing findings highlight the usage of VC learning in dense vision tasks.
  arXiv  Detail & Related papers  (2023-12-02T16:23:52Z)
• Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical [66.57396042747706]
  Complementary-label learning is a weakly supervised learning problem. We propose a consistent approach that does not rely on the uniform distribution assumption. We find that complementary-label learning can be expressed as a set of negative-unlabeled binary classification problems.
  arXiv  Detail & Related papers  (2023-11-27T02:59:17Z)
• Robust Class-Conditional Distribution Alignment for Partial Domain Adaptation [0.7892577704654171]
  Unwanted samples from private source categories in the learning objective of a partial domain adaptation setup can lead to negative transfer and reduce classification performance. Existing methods, such as re-weighting or aggregating target predictions, are vulnerable to this issue. Our proposed approach seeks to overcome these limitations by delving deeper than just the first-order moments to derive distinct and compact categorical distributions.
  arXiv  Detail & Related papers  (2023-10-18T15:49:46Z)
• Domain Generalization via Rationale Invariance [70.32415695574555]
  This paper offers a new perspective to ease the challenge of domain generalization, which involves maintaining robust results even in unseen environments. We propose treating the element-wise contributions to the final results as the rationale for making a decision and representing the rationale for each sample as a matrix. Our experiments demonstrate that the proposed approach achieves competitive results across various datasets, despite its simplicity.
  arXiv  Detail & Related papers  (2023-08-22T03:31:40Z)
• Active Inference-Based Optimization of Discriminative Neural Network Classifiers [3.1219977244201056]
  We propose a novel algorithm to find candidate classification labels of the training samples from their prior probabilities. The proposed objective function could incorporate the candidate labels, the original reference labels, and the priors of the training samples while still being distribution-based.
  arXiv  Detail & Related papers  (2023-06-04T19:30:28Z)
• Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective [89.5370481649529]
  We propose a label distribution perspective for PU learning in this paper. Motivated by this, we propose to pursue the label distribution consistency between predicted and ground-truth label distributions. Experiments on three benchmark datasets validate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-12-06T07:38:29Z)
• Meta Objective Guided Disambiguation for Partial Label Learning [44.05801303440139]
  We propose a novel framework for partial label learning with meta objective guided disambiguation (MoGD) MoGD aims to recover the ground-truth label from candidate labels set by solving a meta objective on a small validation set. The proposed method can be easily implemented by using various deep networks with the ordinary SGD.
  arXiv  Detail & Related papers  (2022-08-26T06:48:01Z)
• Similarity Based Label Smoothing For Dialogue Generation [1.1279808969568252]
  Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Label smoothing enforces a data independent uniform distribution on the incorrect training targets, which leads to an incorrect assumption of equi-probable incorrect targets for each correct target. We propose to transform the uniform distribution of the incorrect target probabilities in label smoothing, to a more natural distribution based on semantics.
  arXiv  Detail & Related papers  (2021-07-23T23:25:19Z)
• Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
  Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
  arXiv  Detail & Related papers  (2020-04-29T10:54:40Z)
• Progressive Identification of True Labels for Partial-Label Learning [112.94467491335611]
  Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. This paper proposes a novel framework of classifier with flexibility on the model and optimization algorithm.
  arXiv  Detail & Related papers  (2020-02-19T08:35:15Z)
• Certified Robustness to Label-Flipping Attacks via Randomized Smoothing [105.91827623768724]
  Machine learning algorithms are susceptible to data poisoning attacks. We present a unifying view of randomized smoothing over arbitrary functions. We propose a new strategy for building classifiers that are pointwise-certifiably robust to general data poisoning attacks.
  arXiv  Detail & Related papers  (2020-02-07T21:28:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.