From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning
Class-Incremental Learning (CIL) requires models to learn new classes without forgetting old ones. A common method is to freeze a pre-trained model and train a new, lightweight adapter for each task. While this prevents forgetting, it treats the learned knowledge as a simple, unstructured collection and fails to use the relationships between tasks. To this end, we propose the Semantic-guided Adaptive Expert Forest (SAEF), a new method that organizes adapters into a structured hierarchy for better knowledge sharing. SAEF first groups tasks into conceptual clusters based on their semantic relationships. Then, within each cluster, it builds a balanced expert tree by creating new adapters from merging the adapters of similar tasks. At inference time, SAEF finds and activates a set of relevant experts from the forest for any given input. The final prediction is made by combining the outputs of these activated experts, weighted by how confident each expert is. Experiments on several benchmark datasets show that SAEF achieves SOTA performance.
Code (0)
등록된 구현이 없습니다.
Tasks
class-incremental learningSimilar Papers 제목 키워드 기반
Preference Isolation Forest for Structure-based Anomaly Detection
We address the problem of detecting anomalies as samples that do not conform to structured patterns represented by low-dimensional manifolds. To this end, we conceive a general anomaly detection framework called Preferen…
Anomaly DetectionInterpretable Anomaly Detection with DIFFI: Depth-based Isolation Forest Feature Importance
Anomaly Detection is an unsupervised learning task aimed at detecting anomalous behaviours with respect to historical data. In particular, multivariate Anomaly Detection has an important role in many applications thanks …
Anomaly DetectionFeature Importancefeature selectionUnsupervised Anomaly DetectionIsolation Mondrian Forest for Batch and Online Anomaly Detection
We propose a new method, named isolation Mondrian forest (iMondrian forest), for batch and online anomaly detection. The proposed method is a novel hybrid of isolation forest and Mondrian forest which are existing method…
Anomaly DetectionEnsemble LearningOut-of-Distribution DetectionOptIForest: Optimal Isolation Forest for Anomaly Detection
Anomaly detection plays an increasingly important role in various fields for critical tasks such as intrusion detection in cybersecurity, financial risk detection, and human health monitoring. A variety of anomaly detect…
Anomaly DetectionBenchmarkingIntrusion DetectionImproved Anomaly Detection by Using the Attention-Based Isolation Forest
A new modification of Isolation Forest called Attention-Based Isolation Forest (ABIForest) for solving the anomaly detection problem is proposed. It incorporates the attention mechanism in the form of the Nadaraya-Watson…
Anomaly Detection