Timezone: »

 
Interpretability of Machine Learning in Computer Systems: Analyzing a Caching Model
Leon Sixt · Evan Liu · Marie Pellat · James Wexler · Milad Hashemi · Been Kim · Martin Maas

Mon Dec 13 01:38 PM -- 01:49 PM (PST) @
in ML For Systems »

Machine Learning has been successfully applied in systems applications such as memory prefetching and caching, where learned models have been shown to outperform heuristics. However, the lack of understanding the inner workings of these models -- interpretability -- remains a major obstacle for adoption in real-world deployments. Understanding a model's behavior can help system administrators and developers gain confidence in the model, understand risks, and debug unexpected behavior in production. Interpretability for models used in computer systems poses a particular challenge: Unlike ML models trained on images or text, the input domain (e.g., memory access patterns, program counters) is not immediately interpretable. A major challenge is therefore to explain the model in terms of concepts that are approachable to a human practitioner. By analyzing a state-of-the-art caching model, we provide evidence that the model has learned concepts beyond simple statistics that can be leveraged for explanations. Our work provides a first step towards understanding ML models in systems and highlights both promises and challenges of this emerging research area.

Author Information

Leon Sixt (Freie Universität Berlin)
Evan Liu (Stanford University)
Marie Pellat (Google)
James Wexler
Milad Hashemi (Google)
Been Kim (Google)
Martin Maas (Google)

More from the Same Authors