# Relational Multi-Task Learning: Modeling Relations between Data and Tasks

arXiv: https://arxiv.org/abs/2303.07666 · HTML: https://mlsanity.com/paper/2303.07666/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 14 Mar 2023.

## Builds on (most cited first, 24 of 24)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Analyzing Learned Molecular Representations for Property Prediction](https://mlsanity.com/paper/1904.01561/) (2019)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Pareto Multi-Task Learning](https://mlsanity.com/paper/1912.12854/) (2019)
- [CNN-RNN: A Unified Framework for Multi-label Image Classification](https://mlsanity.com/paper/1604.04573/) (2016)
- [Few-Shot Video Classification via Temporal Alignment](https://mlsanity.com/paper/1906.11415/) (2019)
- [Robust Learning Through Cross-Task Consistency](https://mlsanity.com/paper/2006.04096/) (2020)
- [Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective](https://mlsanity.com/paper/1906.11081/) (2019)
- [Multi-Label Zero-Shot Learning with Structured Knowledge Graphs](https://mlsanity.com/paper/1711.06526/) (2017)
- [Efficient Continuous Pareto Exploration in Multi-Task Learning](https://mlsanity.com/paper/2006.16434/) (2020)
- [Learning to Propagate for Graph Meta-Learning](https://mlsanity.com/paper/1909.05024/) (2019)
- [Knowledge Graph Transfer Network for Few-Shot Recognition](https://mlsanity.com/paper/1911.09579/) (2019)
- [Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks](https://mlsanity.com/paper/2102.06371/) (2021)

## Built on by (most cited first, 15 of 15)

- [GraphRouter: A Graph-based Router for LLM Selections](https://mlsanity.com/paper/2410.03834/) (2024)
- [PRODIGY: Enabling In-context Learning Over Graphs](https://mlsanity.com/paper/2305.12600/) (2023)
- [Graph World Model](https://mlsanity.com/paper/2507.10539/) (2025)
- [Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions](https://mlsanity.com/paper/2401.02143/) (2024)
- [Graph Sampling-based Meta-Learning for Molecular Property Prediction](https://mlsanity.com/paper/2306.16780/) (2023)
- [MMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving Perception](https://mlsanity.com/paper/2504.02264/) (2025)
- [A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective](https://mlsanity.com/paper/2311.16065/) (2023)
- [Episodic Multi-Task Learning with Heterogeneous Neural Processes](https://mlsanity.com/paper/2310.18713/) (2023)
- [A Pre-training Framework for Relational Data with Information-theoretic Principles](https://mlsanity.com/paper/2507.09837/) (2025)
- [PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling](https://mlsanity.com/paper/2511.16883/) (2025)
- [Fine-Tuning Language Models on Multiple Datasets for Citation Intention Classification](https://mlsanity.com/paper/2410.13332/) (2024)
- [TEM^3-Learning: Time-Efficient Multimodal Multi-Task Learning for Advanced Assistive Driving](https://mlsanity.com/paper/2506.18084/) (2025)
- [MetaEnzyme: Meta Pan-Enzyme Learning for Task-Adaptive Redesign](https://mlsanity.com/paper/2408.10247/) (2024)
- [UV-M3TL: A Unified and Versatile Multimodal Multi-Task Learning Framework for Assistive Driving Perception](https://mlsanity.com/paper/2602.01594/) (2026)
- [Cognitive-Causal Multi-Task Learning with Psychological State Conditioning for Assistive Driving Perception](https://mlsanity.com/paper/2604.07651/) (2026)

## Abstract (arXiv)

A key assumption in multi-task learning is that at the inference time the multi-task model only has access to a given data point but not to the data point's labels from other tasks. This presents an opportunity to extend multi-task learning to utilize data point's labels from other auxiliary tasks, and this way improves performance on the new task. Here we introduce a novel relational multi-task learning setting where we leverage data point labels from auxiliary tasks to make more accurate predictions on the new task. We develop MetaLink, where our key innovation is to build a knowledge graph that connects data points and tasks and thus allows us to leverage labels from auxiliary tasks. The knowledge graph consists of two types of nodes: (1) data nodes, where node features are data embeddings computed by the neural network, and (2) task nodes, with the last layer's weights for each task as node features. The edges in this knowledge graph capture data-task relationships, and the edge label captures the label of a data point on a particular task. Under MetaLink, we reformulate the new task as a link label prediction problem between a data node and a task node. The MetaLink framework provides flexibility to model knowledge transfer from auxiliary task labels to the task of interest. We evaluate MetaLink on 6 benchmark datasets in both biochemical and vision domains. Experiments demonstrate that MetaLink can successfully utilize the relations among different tasks, outperforming the state-of-the-art methods under the proposed relational multi-task learning setting, with up to 27% improvement in ROC AUC.