# Towards Robust Incremental Learning under Ambiguous Supervision

arXiv: https://arxiv.org/abs/2501.13584 · HTML: https://mlsanity.com/paper/2501.13584/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 38 of its 61 references that are in the map.
- First posted on arXiv 23 Jan 2025.

## Builds on (most cited first, 30 of 38)

- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Maintaining Discrimination and Fairness in Class Incremental Learning](https://mlsanity.com/paper/1911.07053/) (2019)
- [Rainbow Memory: Continual Learning with a Memory of Diverse Samples](https://mlsanity.com/paper/2103.17230/) (2021)
- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [Continual Prototype Evolution: Learning Online from Non-Stationary Data Streams](https://mlsanity.com/paper/2009.00919/) (2020)
- [Scalable and Order-robust Continual Learning with Additive Parameter Decomposition](https://mlsanity.com/paper/1902.09432/) (2019)
- [Progressive Identification of True Labels for Partial-Label Learning](https://mlsanity.com/paper/2002.08053/) (2020)
- [Provably Consistent Partial-Label Learning](https://mlsanity.com/paper/2007.08929/) (2020)
- [MagMax: Leveraging Model Merging for Seamless Continual Learning](https://mlsanity.com/paper/2407.06322/) (2024)
- [RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection](https://mlsanity.com/paper/2209.01814/) (2022)
- [MetaGCD: Learning to Continually Learn in Generalized Category Discovery](https://mlsanity.com/paper/2308.11063/) (2023)
- [Weighted Ensemble Models Are Strong Continual Learners](https://mlsanity.com/paper/2312.08977/) (2023)
- [Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning](https://mlsanity.com/paper/2303.09483/) (2023)
- [Prototype-Sample Relation Distillation: Towards Replay-Free Continual Learning](https://mlsanity.com/paper/2303.14771/) (2023)
- [Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning](https://mlsanity.com/paper/2308.09303/) (2023)
- [Make Continual Learning Stronger via C-Flat](https://mlsanity.com/paper/2404.00986/) (2024)
- [Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries](https://mlsanity.com/paper/2203.15355/) (2022)
- [SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning](https://mlsanity.com/paper/2209.10365/) (2022)
- [Continual Semi-Supervised Learning through Contrastive Interpolation Consistency](https://mlsanity.com/paper/2108.06552/) (2021)
- [GM-PLL: Graph Matching based Partial Label Learning](https://mlsanity.com/paper/1901.03073/) (2019)
- [Task-Aware Information Routing from Common Representation Space in Lifelong Learning](https://mlsanity.com/paper/2302.11346/) (2023)
- [On the Robustness of Average Losses for Partial-Label Learning](https://mlsanity.com/paper/2106.06152/) (2021)
- [Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning](https://mlsanity.com/paper/2308.09544/) (2023)
- [Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning](https://mlsanity.com/paper/2402.09542/) (2024)

## Abstract (arXiv)

Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality annotated data in a dynamic learning system can be extremely expensive. To mitigate this problem, we propose a novel weakly-supervised learning paradigm called Incremental Partial Label Learning (IPLL), where the sequentially arrived data relate to a set of candidate labels rather than the ground truth. Technically, we develop the Prototype-Guided Disambiguation and Replay Algorithm (PGDR) which leverages the class prototypes as a proxy to mitigate two intertwined challenges in IPLL, i.e., label ambiguity and catastrophic forgetting. To handle the former, PGDR encapsulates a momentum-based pseudo-labeling algorithm along with prototype-guided initialization, resulting in a balanced perception of classes. To alleviate forgetting, we develop a memory replay technique that collects well-disambiguated samples while maintaining representativeness and diversity. By jointly distilling knowledge from curated memory data, our framework exhibits a great disambiguation ability for samples of new tasks and achieves less forgetting of knowledge. Extensive experiments demonstrate that PGDR achieves superior