# The Traveling Observer Model: Multi-task Learning Through Spatial Variable Embeddings

arXiv: https://arxiv.org/abs/2010.02354 · HTML: https://mlsanity.com/paper/2010.02354/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms](https://mlsanity.com/paper/2305.18409/) (2023)
- [Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach](https://mlsanity.com/paper/2210.12624/) (2022)
- [Out-of-Variable Generalization for Discriminative Models](https://mlsanity.com/paper/2304.07896/) (2023)
- [Interpretable Multi-task Learning with Shared Variable Embeddings](https://mlsanity.com/paper/2405.06330/) (2024)
- [Collaborative Anomaly Detection](https://mlsanity.com/paper/2209.09923/) (2022)
- [Knowledge from Large-Scale Protein Contact Prediction Models Can Be Transferred to the Data-Scarce RNA Contact Prediction Task](https://mlsanity.com/paper/2302.06120/) (2023)
- [Unlocking the Potential of Global Human Expertise](https://mlsanity.com/paper/2411.00156/) (2024)

## Abstract (arXiv)

This paper frames a general prediction system as an observer traveling around a continuous space, measuring values at some locations, and predicting them at others. The observer is completely agnostic about any particular task being solved; it cares only about measurement locations and their values. This perspective leads to a machine learning framework in which seemingly unrelated tasks can be solved by a single model, by embedding their input and output variables into a shared space. An implementation of the framework is developed in which these variable embeddings are learned jointly with internal model parameters. In experiments, the approach is shown to (1) recover intuitive locations of variables in space and time, (2) exploit regularities across related datasets with completely disjoint input and output spaces, and (3) exploit regularities across seemingly unrelated tasks, outperforming task-specific single-task models and multi-task learning alternatives. The results suggest that even seemingly unrelated tasks may originate from similar underlying processes, a fact that the traveling observer model can use to make better predictions.