# Leveraging Organizational Resources to Adapt Models to New Data Modalities

arXiv: https://arxiv.org/abs/2008.09983 · HTML: https://mlsanity.com/paper/2008.09983/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2020.

## Built on by (most cited first, 6 of 6)

- [Language Models in the Loop: Incorporating Prompting into Weak Supervision](https://mlsanity.com/paper/2205.02318/) (2022)
- [Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins](https://mlsanity.com/paper/2106.01501/) (2021)
- [TagRuler: Interactive Tool for Span-Level Data Programming by Demonstration](https://mlsanity.com/paper/2106.12767/) (2021)
- [Making Table Understanding Work in Practice](https://mlsanity.com/paper/2109.05173/) (2021)
- [An Adaptive Method for Weak Supervision with Drifting Data](https://mlsanity.com/paper/2306.01658/) (2023)
- [Leveraging Large Language Models for Structure Learning in Prompted Weak Supervision](https://mlsanity.com/paper/2402.01867/) (2024)

## Abstract (arXiv)

As applications in large organizations evolve, the machine learning (ML) models that power them must adapt the same predictive tasks to newly arising data modalities (e.g., a new video content launch in a social media application requires existing text or image models to extend to video). To solve this problem, organizations typically create ML pipelines from scratch. However, this fails to utilize the domain expertise and data they have cultivated from developing tasks for existing modalities. We demonstrate how organizational resources, in the form of aggregate statistics, knowledge bases, and existing services that operate over related tasks, enable teams to construct a common feature space that connects new and existing data modalities. This allows teams to apply methods for training data curation (e.g., weak supervision and label propagation) and model training (e.g., forms of multi-modal learning) across these different data modalities. We study how this use of organizational resources composes at production scale in over 5 classification tasks at Google, and demonstrate how it reduces the time needed to develop models for new modalities from months to weeks to days.