The increasing popularity of ambient assisted living solutions is claiming adaptive and scalable tools to monitor activities of daily living. Currently, most sensor-based activity recognition techniques rely on supervised learning algorithms. However, the acquisition of comprehensive training sets of activities in smart homes is expensive and violates the individual’s privacy. In this work, we address this problem by proposing a novel hybrid approach that couples collaborative active learning with probabilistic and knowledge-based reasoning. The rationale of our approach is that a generic, and possibly incomplete, knowledge-based model of activities can be refined to target specific individuals and environments by collaboratively acquiring feedback from inhabitants. Specifically, we propose a collaborative active learning method exploiting users’ feedback to (i) refine correlations among sensor events and activity types that are initially extracted from a high-level ontology, and (ii) mine temporal patterns of sensor events that are frequently generated by the execution of specific activities. A Markov Logic Network is used to recognize activities with probabilistic rules that capture both the ontological knowledge and the information obtained by active learning. We experimented our solution with a real-world dataset of activities carried out by several individuals in an interleaved fashion. Experimental results show that our collaborative and personalized active learning solution significantly improves recognition rates, while triggering a small number of feedback requests. Moreover, the overall recognition rates compare favorably with existing supervised and unsupervised activity recognition methods.