# Direct side information learning for zero-shot regression

arXiv: https://arxiv.org/abs/2402.01264 · HTML: https://mlsanity.com/paper/2402.01264/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 76 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 28 of 28)

- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Zero-Shot Relation Extraction via Reading Comprehension](https://mlsanity.com/paper/1706.04115/) (2017)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Zero-Shot Learning Through Cross-Modal Transfer](https://mlsanity.com/paper/1301.3666/) (2013)
- [Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders](https://mlsanity.com/paper/1812.01784/) (2018)
- [f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning](https://mlsanity.com/paper/1903.10132/) (2019)
- [A Review of Generalized Zero-Shot Learning Methods](https://mlsanity.com/paper/2011.08641/) (2020)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2005.00891/) (2020)
- [Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations](https://mlsanity.com/paper/1906.01181/) (2019)
- [HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning](https://mlsanity.com/paper/2109.15163/) (2021)
- [TransZero: Attribute-guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.01683/) (2021)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [Ridge Regression, Hubness, and Zero-Shot Learning](https://mlsanity.com/paper/1507.00825/) (2015)
- [Less is more: zero-shot learning from online textual documents with noise suppression](https://mlsanity.com/paper/1604.01146/) (2016)
- [Zero-Shot Learning via Joint Latent Similarity Embedding](https://mlsanity.com/paper/1511.04512/) (2015)
- [Transductive Zero-Shot Action Recognition by Word-Vector Embedding](https://mlsanity.com/paper/1511.04458/) (2015)
- [Alternative Semantic Representations for Zero-Shot Human Action Recognition](https://mlsanity.com/paper/1706.09317/) (2017)
- [Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review](https://mlsanity.com/paper/2004.14143/) (2020)
- [Spatial-Aware Object Embeddings for Zero-Shot Localization and Classification of Actions](https://mlsanity.com/paper/1707.09145/) (2017)
- [Multi-Target Prediction: A Unifying View on Problems and Methods](https://mlsanity.com/paper/1809.02352/) (2018)
- [A Concise Review of Transfer Learning](https://mlsanity.com/paper/2104.02144/) (2021)
- [Recommender Systems with Heterogeneous Side Information](https://mlsanity.com/paper/1907.08679/) (2019)
- [Hyper-Process Model: A Zero-Shot Learning algorithm for Regression Problems based on Shape Analysis](https://mlsanity.com/paper/1810.10330/) (2018)
- [Zero-Shot Domain Adaptation via Kernel Regression on the Grassmannian](https://mlsanity.com/paper/1507.07830/) (2015)
- [CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context](https://mlsanity.com/paper/2003.11696/) (2020)
- [Zero-Shot Event Detection by Multimodal Distributional Semantic Embedding of Videos](https://mlsanity.com/paper/1512.00818/) (2015)

## Abstract (arXiv)

Zero-shot learning provides models for targets for which instances are not available, commonly called unobserved targets. The availability of target side information becomes crucial in this context in order to properly induce models for these targets. The literature is plenty of strategies to cope with this scenario, but specifically designed on the basis of a zero-shot classification scenario, mostly in computer vision and image classification, but they are either not applicable or easily extensible for a zero-shot regression framework for which a continuos value is required to be predicted rather than a label. In fact, there is a considerable lack of methods for zero-shot regression in the literature. Two approaches for zero-shot regression that work in a two-phase procedure were recently proposed. They first learn the observed target models through a classical regression learning ignoring the target side information. Then, they aggregate those observed target models afterwards exploiting the target side information and the models for the unobserved targets are induced. Despite both have shown quite good performance because of the different treatment they grant to the common features and to the side information, they exploit features and side information separately, avoiding a global optimization for providing the unobserved target models. The proposal of this paper is a novel method that jointly takes features and side information in a one-phase learning process, but treating side information properly and in a more deserving way than as common features. A specific kernel that properly merges features and side information is proposed for this purpose resulting in a novel approach that exhibits better performance over both artificial and real datasets.