This paper studies the synchronization problem of networked uncertain Euler-Lagrange systems with intermittent communication in the presence of irregular communication delays and possible information loss. The interconnection between agents is described by a directed graph containing a spanning tree. Based on the small-gain framework, we propose an adaptive distributed control algorithm to steer all agents' positions to a common position with a prescribed desired velocity available to only some leaders. The communication between agents is intermittent in the sense that neighboring agents exchange their information in a discrete manner with possible packet dropout. Numerical simulation is provided to demonstrate the effectiveness of the proposed synchronization scheme.