Please note: This PhD seminar will take place online.
Ji Xin, PhD candidate
David R. Cheriton School of Computer Science
Supervisors: Professors Jimmy Lin and Yaoliang Yu
There exists a wide variety of efficiency methods for natural language processing (NLP) tasks, such as pruning, distillation, dynamic inference, quantization, etc. We can consider an efficiency method as an operator applied on a model. Naturally, we may construct a pipeline of multiple efficiency methods, i.e., to apply multiple operators on the model sequentially.
In this talk, we discuss the plausibility of this idea, and more importantly, the commutativity and cumulativeness of efficiency operators. We discuss two interesting observations: (1) Efficiency operators are commutative — the order of efficiency methods within the pipeline has little impact on the final results; (2) Efficiency operators are also cumulative — the final results of combining several efficiency methods can be estimated by combining the results of individual methods. These observations deepen our understanding of efficiency operators and provide useful guidelines for building them in real-world applications.