# Deep Contrastive Graph Representation via Adaptive Homotopy Learning

arXiv: https://arxiv.org/abs/2106.09244 · HTML: https://mlsanity.com/paper/2106.09244/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 52 references that are in the map.
- First posted on arXiv 17 Jun 2021.

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

- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Unsupervised Deep Embedding for Clustering Analysis](https://mlsanity.com/paper/1511.06335/) (2015)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Fully-Convolutional Siamese Networks for Object Tracking](https://mlsanity.com/paper/1606.09549/) (2016)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID](https://mlsanity.com/paper/2006.02713/) (2020)
- [Distractor-aware Siamese Networks for Visual Object Tracking](https://mlsanity.com/paper/1808.06048/) (2018)
- [Adversarial Self-Supervised Contrastive Learning](https://mlsanity.com/paper/2006.07589/) (2020)
- [Unsupervised Learning by Predicting Noise](https://mlsanity.com/paper/1704.05310/) (2017)
- [SpectralNet: Spectral Clustering using Deep Neural Networks](https://mlsanity.com/paper/1801.01587/) (2018)
- [Siamese Network for RGB-D Salient Object Detection and Beyond](https://mlsanity.com/paper/2008.12134/) (2020)
- [Adaptive Graph Auto-Encoder for General Data Clustering](https://mlsanity.com/paper/2002.08648/) (2020)
- [Understanding Regularized Spectral Clustering via Graph Conductance](https://mlsanity.com/paper/1806.01468/) (2018)
- [Training Recurrent Neural Networks by Diffusion](https://mlsanity.com/paper/1601.04114/) (2016)
- [A homotopy training algorithm for fully connected neural networks](https://mlsanity.com/paper/1903.09872/) (2019)

## Built on by (most cited first, 2 of 2)

- [Self-supervised Contrastive Attributed Graph Clustering](https://mlsanity.com/paper/2110.08264/) (2021)
- [CNN2GNN: How to Bridge CNN with GNN](https://mlsanity.com/paper/2404.14822/) (2024)

## Abstract (arXiv)

Homotopy model is an excellent tool exploited by diverse research works in the field of machine learning. However, its flexibility is limited due to lack of adaptiveness, i.e., manual fixing or tuning the appropriate homotopy coefficients. To address the problem above, we propose a novel adaptive homotopy framework (AH) in which the Maclaurin duality is employed, such that the homotopy parameters can be adaptively obtained. Accordingly, the proposed AH can be widely utilized to enhance the homotopy-based algorithm. In particular, in this paper, we apply AH to contrastive learning (AHCL) such that it can be effectively transferred from weak-supervised learning (given label priori) to unsupervised learning, where soft labels of contrastive learning are directly and adaptively learned. Accordingly, AHCL has the adaptive ability to extract deep features without any sort of prior information. Consequently, the affinity matrix formulated by the related adaptive labels can be constructed as the deep Laplacian graph that incorporates the topology of deep representations for the inputs. Eventually, extensive experiments on benchmark datasets validate the superiority of our method.