Abstract. Pattern-based model-to-model transformation is a new approach for specifying transformations in a declarative, relational and formal style. The language relies on patterns describing allowed or forbidden relations between two models, which are compiled into operational mechanisms to perform forward and backward transformations. In this paper, we extend the approach for handling attribute conditions expressed in some suitable logic, adapt the operational mechanisms based on graph transformation to relax attribute handling by constraint solving, and discuss heuristics for the compilation of patterns into rules.