LACE: Lightweight Attribution-guided Concept Evolution for Continual Learning

We study concept-bank growth in exemplar-free class-incremental learning. LACE combines task-local concept ranking, an explicit retention budget, and prototype augmentation for old-class training support. We derive the nonnegative form of the specified mean-gradient Concept Attribution (CA) rule and a finite-step loss-decomposition bound. An optional Concept Verification (CV) heuristic compares candidate budgets using a local complexity correction. Archived ImageNet-100 ablations report 900 rather than 1,000 retained coordinates at average accuracy of $93.35\pm 0.46\%$ versus $93.78\pm 0.35\%$ without pruning, with prototype augmentation having the strongest accuracy effect. Source inspection identifies a legacy samplewise CA implementation and test-based selection, so these measurements describe the historical pipeline rather than validate the analyzed rule or an independent held-out protocol. The resulting formulation separates coordinate ranking, budget control, and old-class support, and makes the remaining implementation-verification requirements explicit.