![]() To answer the popular demand, we worked together with PwC to formally support additional fields.ĪrXiv authors and readers value speed and openness, and instant access to publicly available code supports both. Researchers in physics, astronomy, and other fields began adding their work to PwC. After the October release, researchers beyond ML expressed a desire for easy access to relevant code. ![]() This expansion was driven by the broader research community’s demand. And, to better align with our arXiv communities, PwC is launching new sites in computer science, physics, mathematics, astronomy and statistics to help researchers explore code in these fields.Īs part of this expansion, PwC is indexing 600,000 additional papers, automatically detecting and linking to the code libraries for papers in categories beyond Machine Learning and also continuing to identify code, results, and methods within ML.Īuthors can sync their code to display on arXiv abstract pages from either their arXiv user account page or the Papers with Code interface, if the code is not automatically detected. Now, we’re expanding the capability beyond Machine Learning to arXiv papers in every category. Developed in an arXivLabs collaboration with Papers with Code, the tool was met with great enthusiasm from arXiv’s ML community. That improved diversity is further manifested in achieving up to a 14% increase in Hispanic enrollment, 27% increase in Black enrollment, and 60% increase in Asian enrollment compared to selecting sites with an enrollment-only model.In October, arXiv released a new feature empowering arXiv authors to link their Machine Learning articles to associated code. Specifically, it is able to produce a 9% improvement in diversity with similar enrollment levels over the leading baselines. We evaluate FRAMM using 4,392 real-world clinical trials ranging from 2016 to 2021 and show that FRAMM outperforms the leading baseline in enrollment-only settings while also achieving large gains in diversity. ![]() To handle the need for making efficient trade-offs, FRAMM uses deep reinforcement learning with a specifically designed reward function that simultaneously optimizes for both enrollment and fairness. To address the missing data challenge, FRAMM has a modality encoder with a masked cross-attention mechanism for handling missing data, bypassing data imputation and the need for complete data in training. We focus on addressing two real-world challenges that affect fair trial sites selection: the data modalities are often not complete for many potential trial sites, and the site selection needs to simultaneously optimize for both enrollment and diversity since the problem is necessarily a trade-off between the two with the only possible way to increase diversity post-selection being through limiting enrollment via caps. This paper focuses on the trial site selection task and proposes FRAMM, a deep reinforcement learning framework for fair trial site selection. Despite many efforts to address the disparities, the underrepresentation of gender, racial, and ethnic minorities in clinical trials remains a problem and undermines the efficacy of treatments on minorities. Paper Code Bridging Control-Centric and Data-Centric Optimization spcl/mlir-dace With the rise of specialized hardware and new programming languages, code optimization has shifted its focus towards promoting data locality.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |