Model Releases
Provenance Guided Incremental Learning Under Evolving Concept Definitions
arXiv:2608.23893v1 Announce Type: new Abstract: Learning systems deployed over long periods must adapt not only to statistical changes in incoming data, but also to revisions of the definitions that g
arXiv:2608.23893v1 Announce Type: new Abstract: Learning systems deployed over long periods must adapt not only to statistical changes in incoming data, but also to revisions of the definitions that generate their prediction targets. Conventional concept-drift methods typically infer such changes from observations or prediction errors, even when the underlying policy, rule, or query has been explicitly modified. This paper studies rule-induced concept shift, where the target-defining concept is revised directly, causing previously stored instances to acquire different semantic labels without requiring any change in their observed data. We introduce a provenance-guided incremental learning framework that compiles consecutive concept definitions into a structured rule delta, traces the changed components through historical provenance, certifies records whose previous labels remain valid, and restricts reevaluation to a localized candidate region. Executable revisions are relabeled automatically, ambiguous cases are handled through selective supervision, and the resulting changes are used for incremental predictor repair. A versioned concept memory further supports recurring definitions. We also introduce RuleShift-Bench, spanning financial, demographic, cybersecurity, and graph-structured data with threshold, predicate, logical, relational, recurring, and mixed concept revisions. Across the benchmark, provenance-guided repair attains 92.3% accuracy and 90.2% Macro-F1 while reprocessing 14.7% of the historical collection and retaining 94.6% of affected records. Its average update latency is 179s compared with 993s for complete relabeling and retraining. The results demonstrate that an explicit concept revision can be exploited as a data-maintenance signal, allowing learning systems to update the supervision and predictive state that depend on the change while preserving knowledge that remains valid.
Related
- BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
- BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
- Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition
- MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs
- Representation Finetuning for Continual Learning
Source: arXiv cs.AI | 2026-08-26