Selecting good conference keywords is important because they often determine the composition of review committees and hence which papers are reviewed by whom. But presently conference keywords are generated in an ad-hoc manner by a small set of conference organizers. This approach is plainly not ideal. There is no guarantee, for example, that the generated keyword set aligns with what the community is actually working on and submitting to the conference in a given year. This is especially true in fast moving fields such as AI. The problem is exacerbated by the tendency of organizers to draw heavily on preceding years' keyword lists when generating a new set. Rather than a select few ordaining a keyword set that that represents AI at large, it would be preferable to generate these keywords more directly from the data, with input from research community members. To this end, we solicited feedback from seven AAAI PC members regarding a previously existing keyword set and used these 'community-sourced constraints' to inform a clustering over the abstracts of all submissions to AAAI 2013. We show that the keywords discovered via this data-driven, human-in-the-loop method are at least as preferred (by AAAI PC members) as 2013's manually generated set, and that they include categories previously overlooked by organizers. Many of the discovered terms were used for this year's conference.

Machine learning research is often conducted in vitro, divorced from motivating practical applications. In terms of advancing machine learning as an academic discipline, this approach has thus far proven quite fruitful. However, it is our view that the most interesting open problems in machine learning are those that arise during its application to real-world problems. We illustrate this point by reviewing two of our interdisciplinary collaborations, both of which have posed unique machine learning problems, providing fertile ground for novel research.

Machine learning research is often conducted in vitro, divorced from motivating practical applications. A researcher might develop a new method for the general task of classification, then assess its utility by comparing its performance (such as accuracy or AUC) to that of existing classification models on publicly available datasets. In terms of advancing machine learning as an academic discipline, this approach has thus far proven quite fruitful. However, it is our view that the most interesting open problems in machine learning are those that arise during its application to real-world problems. We illustrate this point by reviewing two of our interdisciplinary collaborations, both of which have posed unique machine learning problems, providing fertile ground for novel research.

Program execution speed on modem computers is sensitive, by a factor of two or more, to the order in which instructions are presented to the processor. Torealize potential execution efficiency, an optimizing compiler must employ a heuristic algorithm for instruction scheduling. Such algorithms are painstakingly handcrafted, which is expensive and time-consuming. We show how to cast the instruction scheduling problem as a learning task, obtaining theheuristic scheduling algorithm automatically. Our focus is the narrower problem of scheduling straight-line code (also called basic blocks of instructions). Our empirical results show that just a few features are adequate forquite good performance at this task for a real modem processor, and that any of several supervised learning methods perform nearly optimally withrespect to the features used.

Program execution speed on modem computers is sensitive, by a factor of two or more, to the order in which instructions are presented to the processor. To realize potential execution efficiency, an optimizing compiler must employ a heuristic algorithm for instruction scheduling. Such algorithms are painstakingly handcrafted, which is expensive and time-consuming. We show how to cast the instruction scheduling problem as a learning task, obtaining the heuristic scheduling algorithm automatically. Our focus is the narrower problem of scheduling straight-line code (also called basic blocks of instructions). Our empirical results show that just a few features are adequate for quite good performance at this task for a real modem processor, and that any of several supervised learning methods perform nearly optimally with respect to the features used.