Asynchronous message passing for large graph clustering

A computer-implemented method comprising:

• propagating, using at least one processor, messages sent between nodes in a distributed graph in an intelligently asynchronous manner that includes bundling together messages directed to nodes on another leaf server before the propagation of the messages and skipping redundant messages rather than propagating the redundant messages, the messages including respective cluster identifiers, wherein a priority queue engine controls the propagating;
• and
• in response to a first node of the distributed graph receiving one of the messages:
• comparing, using the at least one processor, a cluster identifier from the received message with a cluster identifier for the first node to determine whether to update the cluster identifier for the first node, and
• when it is determined that the cluster identifier of the first node is to be updated:
• updating the cluster identifier for the first node with the cluster identifier from the message, and
• sending messages to neighboring nodes of the first node via the priority queue, the messages including the updated cluster identifier.

A computer-implemented method comprising:

• receiving, using at least one processor, at a node in a distributed graph, a message with a first value;
• determining, at the node, that the first value replaces a current value for the node;
• responsive to the determining, setting a status of the node to active and sending messages that include the first value to neighboring nodes;
• and
• receiving, using the at least one processor, the messages to the neighboring nodes at a priority queue, wherein the priority queue propagates messages in an intelligently asynchronous manner that includes bundling together messages directed to nodes on another leaf server before the propagation of the messages and skipping redundant messages rather than propagating the redundant messages, and wherein responsive to the message being propagated to the neighboring nodes, the status of the node is set to inactive.