# GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery

arXiv: https://arxiv.org/abs/2602.19872 · HTML: https://mlsanity.com/paper/2602.19872/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training](https://mlsanity.com/paper/2101.12699/) (2021)
- [Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path](https://mlsanity.com/paper/2106.02073/) (2021)
- [Parametric Classification for Generalized Category Discovery: A Baseline Study](https://mlsanity.com/paper/2211.11727/) (2022)
- [PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery](https://mlsanity.com/paper/2212.05590/) (2022)
- [Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery](https://mlsanity.com/paper/2305.06144/) (2023)
- [Dissecting Supervised Contrastive Learning](https://mlsanity.com/paper/2102.08817/) (2021)
- [MetaGCD: Learning to Continually Learn in Generalized Category Discovery](https://mlsanity.com/paper/2308.11063/) (2023)
- [Parametric Information Maximization for Generalized Category Discovery](https://mlsanity.com/paper/2212.00334/) (2022)
- [Contrastive Mean-Shift Learning for Generalized Category Discovery](https://mlsanity.com/paper/2404.09451/) (2024)
- [Grow and Merge: A Unified Framework for Continuous Categories Discovery](https://mlsanity.com/paper/2210.04174/) (2022)
- [Happy: A Debiased Learning Framework for Continual Generalized Category Discovery](https://mlsanity.com/paper/2410.06535/) (2024)
- [DualCP: Rehearsal-Free Domain-Incremental Learning via Dual-Level Concept Prototype](https://mlsanity.com/paper/2503.18042/) (2025)
- [Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery](https://mlsanity.com/paper/2507.04725/) (2025)

## Built on by (most cited first, 1 of 1)

- [Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery](https://mlsanity.com/paper/2603.19918/) (2026)

## Abstract (arXiv)

Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamically, resulting in forgetting and inconsistent feature alignment. We propose GOAL, a unified framework that introduces a fixed Equiangular Tight Frame (ETF) classifier to impose a consistent geometric structure throughout learning. GOAL conducts supervised alignment for labeled samples and confidence-guided alignment for novel samples, enabling stable integration of new classes without disrupting old ones. Experiments on four benchmarks show that GOAL outperforms the prior method Happy, reducing forgetting by 16.1% and boosting novel class discovery by 3.2%, establishing a strong solution for long-horizon continual discovery.