The paper introduces a provenance-guided incremental learning framework that handles rule-induced concept shift, where target definitions are explicitly revised and previously stored instances receive new semantic labels. By compiling concept changes into structured rule deltas, tracing affected records through historical provenance, and selectively re-evaluating only a localized candidate region, the method automatically relabels executable revisions, manages ambiguous cases with selective supervision, and repairs predictors incrementally. Evaluation on the RuleShift-Bench benchmark—covering financial, demographic, cybersecurity, and graph-structured data—shows 92.3% accuracy and 90.2% Macro‑F1, reprocessing only 14.7% of the historical collection and achieving an average update latency of 179 s versus 993 s for full relabeling and retraining.
arXiv:2608.23903v1 Announce Type: new Abstract: Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the pr...
Visual foundation models are commonly adapted under the assumption that the appearance of incoming data may change while the semantic meaning of the prediction task remains fixed. In long-lived visual...
The paper presents an incremental Learner Digital Twin that uses a lightweight knowledge graph to provide evidence‑grounded early warning in learning analytics. The twin is updated at temporal checkpoints by replaying learning traces and assessment records, enabling both feature extraction and explanation grounding. Evaluated on a public benchmark, the graph‑mediated approach preserves predictive performance while generating alerts that link risk decisions to specific evidence items and raw records.
LakeHopper is a method for adapting column type annotators (CTA) from one data lake to another by treating cross‑lake adaptation as a knowledge‑management problem. It decomposes the source annotator’s knowledge into source‑specific, shared, and target‑specific parts, and then uses three mechanisms—label‑set realignment, LLM‑verified gap discovery, and cluster‑based propagation with rehearsal fine‑tuning—to adapt the annotator under a limited annotation budget. The approach achieves up to a 71.4% relative macro‑F1 improvement over three PLM backbones, reaches near‑full data quality with less than 6% of target labels, and trains 27–131 times faster than fine‑tuned table LLMs.
arXiv:2610.07008v1 Announce Type: new Abstract: Few-shot class-incremental learning (FSCIL) aims to learn novel classes from limited annotations while preserving prior knowledge. Existing methods typ...
arXiv:2609.36559v1 Announce Type: cross Abstract: Extrapolative temporal knowledge graph reasoning (TKGR) predicts future facts from historical snapshots. Most existing methods train once on an early...
arXiv:2603.12677v4 Announce Type: replace-cross Abstract: Existing locate-then-edit Knowledge Editing (KE) methods typically decompose editing into two stages: upstream target representation optimiza...
arXiv:2607. 08646v1 Announce Type: cross Abstract: As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish.
CLEAN (Continual Learning with Expandable and Architecturally Isolated Networks) is an incremental cognitive diagnosis framework that allows the concept space to grow while guaranteeing that historical diagnoses remain unchanged. It achieves this by freezing past diagnostic functions, applying orthogonal column masking to prevent gradient interference, and adding expandable full‑rank branches with micro‑variance initialization for new concepts. Experiments on three large‑scale educational datasets show that CLEAN attains zero Representation Drift, preserving old‑item metrics exactly while performing competitively on new items.
The paper demonstrates that off‑policy merging, called grafting, outperforms on‑policy self‑distillation for continual learning. Grafting learns updates on an earlier donor checkpoint, scales the update, and optionally masks sensitive directions, thereby reducing interference with existing capabilities. Across various continual learning scenarios, grafting achieves better new‑task and old‑task performance without costly on‑policy sampling.
arXiv:2608. 11022v1 Announce Type: cross Abstract: Model Cards and Data Cards have demonstrated the value of structured, human-readable documentation for machine learning artifacts, capturing their context, parameters, limitations, and intended use.
arXiv:2604. 01904v3 Announce Type: replace-cross Abstract: Post-hoc unauthorized-training data detection for large language models (LLMs) typically assumes a query-with-originals regime: rights holders query a target LLM with raw proprietary data and assess whether the model assigns them stronger memorization-based detection signals, e.