# A Unified Perspective on Multi-Domain and Multi-Task Learning

arXiv: https://arxiv.org/abs/1412.7489 · HTML: https://mlsanity.com/paper/1412.7489/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2014.

## Built on by (most cited first, 30 of 33)

- [One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction](https://mlsanity.com/paper/2101.11427/) (2021)
- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.06536/) (2021)
- [Knowledge-aware Zero-Shot Learning: Survey and Perspective](https://mlsanity.com/paper/2103.00070/) (2021)
- [Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities](https://mlsanity.com/paper/2202.03630/) (2022)
- [Domain Generalization through Meta-Learning: A Survey](https://mlsanity.com/paper/2404.02785/) (2024)
- [On Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization and Beyond](https://mlsanity.com/paper/2203.09513/) (2022)
- [Automatic Expert Selection for Multi-Scenario and Multi-Task Search](https://mlsanity.com/paper/2205.14321/) (2022)
- [UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions](https://mlsanity.com/paper/2310.02973/) (2023)
- [Learning to Transfer for Traffic Forecasting via Multi-task Learning](https://mlsanity.com/paper/2111.15542/) (2021)
- [A Survey on Visual Transfer Learning using Knowledge Graphs](https://mlsanity.com/paper/2201.11794/) (2022)
- [CIZSL++: Creativity Inspired Generative Zero-Shot Learning](https://mlsanity.com/paper/2101.00173/) (2021)
- [A separability-based approach to quantifying generalization: which layer is best?](https://mlsanity.com/paper/2405.01524/) (2024)
- [Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn](https://mlsanity.com/paper/2305.07625/) (2023)
- [Provable Adaptation across Multiway Domains via Representation Learning](https://mlsanity.com/paper/2106.06657/) (2021)
- [Elastic Multi-Gradient Descent for Parallel Continual Learning](https://mlsanity.com/paper/2401.01054/) (2024)
- [Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives](https://mlsanity.com/paper/2505.21598/) (2025)
- [Multi-Domain Learning by Meta-Learning: Taking Optimal Steps in Multi-Domain Loss Landscapes by Inner-Loop Learning](https://mlsanity.com/paper/2102.13147/) (2021)
- [Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning](https://mlsanity.com/paper/2309.10302/) (2023)
- [Parameter-efficient Multi-Task and Multi-Domain Learning using Factorized Tensor Networks](https://mlsanity.com/paper/2310.06124/) (2023)
- [Interpretable Multi-task Learning with Shared Variable Embeddings](https://mlsanity.com/paper/2405.06330/) (2024)
- [Evaluating Transfer Learning Methods on Real-World Data Streams: A Case Study in Financial Fraud Detection](https://mlsanity.com/paper/2508.02702/) (2025)
- [Federated Learning via Meta-Variational Dropout](https://mlsanity.com/paper/2510.20225/) (2025)
- [Predictive Optimization with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2101.06233/) (2021)
- [A microservice-based framework for exploring data selection in cross-building knowledge transfer](https://mlsanity.com/paper/2102.12970/) (2021)
- [Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification](https://mlsanity.com/paper/2102.13322/) (2021)
- [Zero-Shot Learning Based on Knowledge Sharing](https://mlsanity.com/paper/2102.13326/) (2021)
- [Robust Representation Learning for Unified Online Top-K Recommendation](https://mlsanity.com/paper/2310.15492/) (2023)
- [A Multi-Domain Multi-Task Approach for Feature Selection from Bulk RNA Datasets](https://mlsanity.com/paper/2405.02534/) (2024)
- [Multi-Attribute Multi-Grained Adaptation of Pre-Trained Language Models for Text Understanding from Bayesian Perspective](https://mlsanity.com/paper/2503.06085/) (2025)

## Abstract (arXiv)

In this paper, we provide a new neural-network based perspective on multi-task learning (MTL) and multi-domain learning (MDL). By introducing the concept of a semantic descriptor, this framework unifies MDL and MTL as well as encompassing various classic and recent MTL/MDL algorithms by interpreting them as different ways of constructing semantic descriptors. Our interpretation provides an alternative pipeline for zero-shot learning (ZSL), where a model for a novel class can be constructed without training data. Moreover, it leads to a new and practically relevant problem setting of zero-shot domain adaptation (ZSDA), which is the analogous to ZSL but for novel domains: A model for an unseen domain can be generated by its semantic descriptor. Experiments across this range of problems demonstrate that our framework outperforms a variety of alternatives.