# Column Networks for Collective Classification

arXiv: https://arxiv.org/abs/1609.04508 · HTML: https://mlsanity.com/paper/1609.04508/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2016.

## Built on by (most cited first, 17 of 17)

- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Graph-based Semi-supervised Learning: A Comprehensive Review](https://mlsanity.com/paper/2102.13303/) (2021)
- [Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey](https://mlsanity.com/paper/2203.10480/) (2022)
- [NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/2106.11865/) (2021)
- [Unitary convolutions for learning on graphs and groups](https://mlsanity.com/paper/2410.05499/) (2024)
- [Graph Convolutional Networks for Multi-modality Medical Imaging: Methods, Architectures, and Clinical Applications](https://mlsanity.com/paper/2202.08916/) (2022)
- [Semi-Supervised Deep Learning for Multiplex Networks](https://mlsanity.com/paper/2110.02038/) (2021)
- [Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networks](https://mlsanity.com/paper/2209.06589/) (2022)
- [Residual Network and Embedding Usage: New Tricks of Node Classification with Graph Convolutional Networks](https://mlsanity.com/paper/2105.08330/) (2021)
- [Comprehensive Analysis of Over-smoothing in Graph Neural Networks from Markov Chains Perspective](https://mlsanity.com/paper/2211.06605/) (2022)
- [Statistical physics analysis of graph neural networks: Approaching optimality in the contextual stochastic block model](https://mlsanity.com/paper/2503.01361/) (2025)
- [Graphfool: Targeted Label Adversarial Attack on Graph Embedding](https://mlsanity.com/paper/2102.12284/) (2021)
- [Asymmetric Graph Representation Learning](https://mlsanity.com/paper/2110.07436/) (2021)
- [TextRGNN: Residual Graph Neural Networks for Text Classification](https://mlsanity.com/paper/2112.15060/) (2021)
- [Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation](https://mlsanity.com/paper/2312.17301/) (2023)
- [One-Shot Learning on Attributed Sequences](https://mlsanity.com/paper/2201.09202/) (2022)
- [Forecasting West Nile virus with deep graph encoders](https://mlsanity.com/paper/2509.22657/) (2025)

## Abstract (arXiv)

Relational learning deals with data that are characterized by relational structures. An important task is collective classification, which is to jointly classify networked objects. While it holds a great promise to produce a better accuracy than non-collective classifiers, collective classification is computational challenging and has not leveraged on the recent breakthroughs of deep learning. We present Column Network (CLN), a novel deep learning model for collective classification in multi-relational domains. CLN has many desirable theoretical properties: (i) it encodes multi-relations between any two instances; (ii) it is deep and compact, allowing complex functions to be approximated at the network level with a small set of free parameters; (iii) local and relational features are learned simultaneously; (iv) long-range, higher-order dependencies between instances are supported naturally; and (v) crucially, learning and inference are efficient, linear in the size of the network and the number of relations. We evaluate CLN on multiple real-world applications: (a) delay prediction in software projects, (b) PubMed Diabetes publication classification and (c) film genre classification. In all applications, CLN demonstrates a higher accuracy than state-of-the-art rivals.