mlsanityData to 7 Oct 2026

Application-Driven Innovation in Machine Learning

arXiv 2403.17381 ↗First posted 26 Mar 2024cs.LG cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

In this position paper, we argue that application-driven research has been systemically under-valued in the machine learning community. As applications of machine learning proliferate, innovative algorithms inspired by specific real-world challenges have become increasingly important. Such work offers the potential for significant impact not merely in domains of application but also in machine learning itself. In this paper, we describe the paradigm of application-driven research in machine learning, contrasting it with the more standard paradigm of methods-driven research. We illustrate the benefits of application-driven machine learning and how this approach can productively synergize with methods-driven work. Despite these benefits, we find that reviewing, hiring, and teaching practices in machine learning often hold back application-driven innovation. We outline how these processes may be improved.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 31 of its 59 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

31 of 59 references.

References · 31

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  6. 2016OpenAI Gymcited by 1,684
  7. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  8. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 326
  9. 2019Tackling Climate Change with Machine Learningcited by 264
  10. 2020Large image datasets: A pyrrhic win for computer vision?cited by 237
  11. 2022FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operatorscited by 188
  12. 2021The Values Encoded in Machine Learning Researchcited by 172
19 more
  1. 2023SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagerycited by 148
  2. 2022Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)cited by 137
  3. 2019Presence-Only Geographical Priors for Fine-Grained Image Classificationcited by 109
  4. 2018Troubling Trends in Machine Learning Scholarshipcited by 107
  5. 2023Lightweight, Pre-trained Transformers for Remote Sensing Timeseriescited by 102
  6. 2023FAENet: Frame Averaging Equivariant GNN for Materials Modelingcited by 72
  7. 2018A Review of Challenges and Opportunities in Machine Learning for Healthcited by 67
  8. 2021Learning to run a Power Network Challenge: a Retrospective Analysiscited by 52
  9. 2021PASS: An ImageNet replacement for self-supervised pretraining without humanscited by 51
  10. 2021Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Healthcited by 43
  11. 2020Enforcing robust control guarantees within neural network policiescited by 40
  12. 2021Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimizationcited by 31
  13. 2020CityLearn: Standardizing Research in Multi-Agent Reinforcement Learning for Demand Response and Urban Energy Managementcited by 27
  14. 2022Bugs in the Data: How ImageNet Misrepresents Biodiversitycited by 24
  15. 2023Fourier Neural Operators for Arbitrary Resolution Climate Data Downscalingcited by 24
  16. 2021The Need for Ethical, Responsible, and Trustworthy Artificial Intelligence for Environmental Sciencescited by 12
  17. 2022Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Healthcited by 12
  18. 2022TIML: Task-Informed Meta-Learning for Agriculturecited by 7
  19. 2022Modern Machine Learning Tools for Monitoring and Control of Industrial Processes: A Surveycited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 10; 2026: 7.

24 papers.

Sort:

By area:

  1. 2024The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applicationscited by 17
  2. 2024AstroPT: Scaling Large Observation Models for Astronomycited by 9
  3. 2024DOLOMITES: Domain-Specific Long-Form Methodical Taskscited by 8
  4. 2024IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learningcited by 6
  5. 2025SelvaBox: A high-resolution dataset for tropical tree crown detectioncited by 5
  6. 2026SelvaMask: Segmenting Trees in Tropical Forests and Beyondcited by 5
  7. 2025Position: Biology is the Challenge Physics-Informed ML Needs to Evolvecited by 4
  8. 2025AI for Just Work: Constructing Diverse Imaginations of AI beyond "Replacing Humans"cited by 2
  9. 2025Position: We Need Responsible, Application-Driven (RAD) AI Researchcited by 2
  10. 2025Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standardscited by 2
  11. 2024Improving satellite imagery segmentation using multiple Sentinel-2 revisitscited by 1
  12. 2024RL for Mitigating Cascading Failures: Targeted Exploration via Sensitivity Factorscited by 1
12 more
  1. 2025Towards Application-Specific Evaluation of Vision Models: Case Studies in Ecology and Biologycited by 1
  2. 2026MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applicationscited by 1
  3. 2026Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxycited by 1
  4. 2024A Research Agenda for Usability and Generalisation in Reinforcement Learningcited by 0
  5. 2025Geospatial Artificial Intelligence for Satellite-Based Flood Extent Mapping: Concepts, Advances, and Future Perspectivescited by 0
  6. 2025kabr-tools: Automated Framework for Multi-Species Behavioral Monitoringcited by 0
  7. 2025Mass Conservation on Rails -- Rethinking Physics-Informed Learning of Ice Flow Vector Fieldscited by 0
  8. 2025BioBench: A Blueprint to Move Beyond ImageNet for Scientific ML Benchmarkscited by 0
  9. 2026DynaSTy: A Framework for SpatioTemporal Node Attribute Prediction in Dynamic Graphscited by 0
  10. 2026CHIRP dataset: towards long-term, individual-level, behavioral monitoring of bird populations in the wildcited by 0
  11. 2026AI Meets Mathematics Education: A Case Study on Supporting an Instructor in a Large Mathematics Class with Context-Aware AIcited by 0
  12. 2026Learning to Cover Locally: Graph Neural Combinatorial Optimization under a Hard Information Horizoncited by 0