Graph-Explanation-Guided Layer Fusion for Deep Neural Network Inference
A method that applies Graph Explanation Techniques (explainable-AI attributions over graph-structured models) to deep-neural-network layer fusion. When a fusion group is invalid because it exceeds an accelerator's on-chip buffer, graph explanation identifies the operations most responsible for the invalidity and a greedy tree-based algorithm recursively splits the group along them to minimize DRAM accesses, reducing inference data movement on convolutional networks.
2501.00636
A method that brings Graph Explanation Techniques (explainable-AI attributions over graph-structured models) into deep-neural-network layer fusion. A DNN is cast as a directed acyclic graph and parti…