Meta-Neighborhoods

2019-09-18 · NeurIPS 2020 12 · Siyuan Shan, Yang Li, Junier Oliva

Making an adaptive prediction based on one's input is an important ability for general artificial intelligence. In this work, we step forward in this direction and propose a semi-parametric method, Meta-Neighborhoods, where predictions are made adaptively to the neighborhood of the input. We show that Meta-Neighborhoods is a generalization of $k$-nearest-neighbors. Due to the simpler manifold structure around a local neighborhood, Meta-Neighborhoods represent the predictive distribution $p(y \mid x)$ more accurately. To reduce memory and computation overhead, we propose induced neighborhoods that summarize the training data into a much smaller dictionary. A meta-learning based training mechanism is then exploited to jointly learn the induced neighborhoods and the model. Extensive studies demonstrate the superiority of our method.

📄 PDF Abstract BibTeX arXiv:1909.09140

Code (1)

lupalab/Meta-Neighborhoods 공식 구현 tf

Tasks

Meta-Learning Multi-Task Learning

Transforming Constraint Programs to Input for Local Search

2026-05-19 · Jo Devriendt, Patrick De Causmaecker, Marc Denecker arxiv

Applying local search algorithms to combinatorial optimization problems is not an easy feat. Typically, human intervention is required to compile the constraints to input data for some metaheuristic algorithm. In this pa…

3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence

2020-10-21 · Hao Huang, Lingjing Wang, Xiang Li, Yi Fang

Point signature, a representation describing the structural neighborhood of a point in 3D shapes, can be applied to establish correspondences between points in 3D shapes. Conventional methods apply a weight-sharing netwo…

3D Dense Shape Correspondence Meta-Learning

FOCAL-Attention for Heterogeneous Multi-Label Prediction

2026-04-21 · Chenghao Zhang, Qingqing Long, Ludi Wang, Wenjuan Cui 외 arxiv

Heterogeneous graphs have attracted increasing attention for modeling multi-typed entities and relations in complex real-world systems. Multi-label node classification on heterogeneous graphs is challenging due to struct…

Node Classification

Love Thy Neighbors: Image Annotation by Exploiting Image Metadata

2015-08-30 · ICCV 2015 12 · Justin Johnson, Lamberto Ballan, Fei-Fei Li

Some images that are difficult to recognize on their own may become more clear in the context of a neighborhood of related images with similar social-network metadata. We build on this intuition to improve multilabel ima…

Interval Bound Interpolation for Few-shot Learning with Few Tasks

2022-04-07 · Shounak Datta, Sankha Subhra Mullick, Anish Chakrabarty, Swagatam Das

Few-shot learning aims to transfer the knowledge acquired from training on a diverse set of tasks to unseen tasks from the same task distribution with a limited amount of labeled data. The underlying requirement for effe…

Few-Shot Learning Meta-Learning Metric Learning