# MetaMIML: Meta Multi-Instance Multi-Label Learning

arXiv: https://arxiv.org/abs/2111.04112 · HTML: https://mlsanity.com/paper/2111.04112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 35 references that are in the map.
- First posted on arXiv 7 Nov 2021.

## Builds on (most cited first, 9 of 9)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Meta Networks](https://mlsanity.com/paper/1703.00837/) (2017)
- [MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation](https://mlsanity.com/paper/1908.00413/) (2019)
- [Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark](https://mlsanity.com/paper/2004.00216/) (2020)
- [Fast Multi-Instance Multi-Label Learning](https://mlsanity.com/paper/1310.2049/) (2013)
- [Data Fusion by Matrix Factorization](https://mlsanity.com/paper/1307.0803/) (2013)
- [Multi-View Multi-Instance Multi-Label Learning based on Collaborative Matrix Factorization](https://mlsanity.com/paper/1905.05061/) (2019)

## Abstract (arXiv)

Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances. Current MIML solutions still focus on a single-type of objects and assumes an IID distribution of training data. But these objects are linked with objects of other types, %(i.e., pictures in Facebook link with various users), which also encode the semantics of target objects. In addition, they generally need abundant labeled data for training. To effectively mine interdependent MIML objects of different types, we propose a network embedding and meta learning based approach (MetaMIML). MetaMIML introduces the context learner with network embedding to capture semantic information of objects of different types, and the task learner to extract the meta knowledge for fast adapting to new tasks. In this way, MetaMIML can naturally deal with MIML objects at data level improving, but also exploit the power of meta-learning at the model enhancing. Experiments on benchmark datasets demonstrate that MetaMIML achieves a significantly better performance than state-of-the-art algorithms.