OFIGM: Online Feature-Instance Graph Memory for Open-World Class-Incremental Learning

Real-world data streams are inherently open and nonstationary: previously unseen classes may emerge, labels can be sparse or delayed, and the observable feature space itself may evolve over time. However, existing continual, open-world, and streaming learning methods typically address these challenges in isolation. We propose OFIGM, an Online Feature-Instance Graph Memory framework for open-world class-incremental learning under simultaneous class and feature evolution. OFIGM maintains a bounded dynamic bipartite graph comprising transient instance nodes and persistent feature nodes, performs sparse graph message passing to learn schema-adaptive representations, and preserves previously acquired class knowledge through slowly updated prototype memory. A graph-aware novelty score integrates prototype distance, predictive uncertainty, and structural residuals to identify unknown samples, while a persistence-aware unknown buffer promotes coherent novel groups to new classes without global retraining. Across Digits, Wine, and Iris, OFIGM achieves mean Macro-F1 of $0.819$, novel-class F1 of $0.882$, and novelty AUROC of $0.866$. Relative to a matched no-graph ablation, graph memory improves novelty AUROC from $0.926$ to $0.946$ on Wine and from $0.755$ to $0.794$ on Iris. We further evaluate generalization on an external Louisiana shellfish outbreak dataset containing 11 documented episodes from 2002-2025, where OFIGM achieves Macro-F1 of $0.474$ and outbreak recall of $0.787$. These results demonstrate the feasibility of persistent feature-instance graph memory as a unified mechanism for novel-class detection, incremental class creation, and continual adaptation in evolving open-world streams.