Recurrent collective classification

@article{Fan2017RecurrentCC,
  title={Recurrent collective classification},
  author={Shuangfei Fan and Bert Huang},
  journal={Knowledge and Information Systems},
  year={2017},
  pages={1-15}
}
We propose a new method for training iterative collective classifiers for labeling nodes in network data. The iterative classification algorithm (ICA) is a canonical method for incorporating relational information into classification. Yet, existing methods for training ICA models rely on the assumption that relational features reflect the true labels of the nodes. This unrealistic assumption introduces a bias that is inconsistent with the actual prediction algorithm. In this paper, we introduce… 

A Collective Learning Framework to Boost GNN Expressiveness

This work considers the task of inductive node classification using GNNs in supervised and semi-supervised settings, with the goal of incorporating label dependencies, and proposes a general collective learning approach to increase the representation power of any existing GNN.

Representation Learning for Classification in Heterogeneous Graphs with Application to Social Networks

A transductive approach to classification that learns to project the different types of nodes into a common latent space, and embedding is learned so as to reflect different characteristics of the problem such as the correlation between node labels, as well as the graph topology.

Relational Classification of Biological Cells in Microscopy Images

A Relational Long Short-Term Memory algorithm, coupled with auto-encoders and convolutional neural networks, that can learn from both annotated and unlabeled microscopy images and that can utilize both the local and neighborhood information to perform an improved classification of biological cells is proposed.

On the Equivalence between Positional Node Embeddings and Structural Graph Representations

This work provides the first unifying theoretical framework for node embeddings and structural graph representations, bridging methods like matrix factorization and graph neural networks, and introduces new practical guidelines to generating and using nodeembeddings, which further augments standard operating procedures used today.

On the Equivalence between Node Embeddings and Structural Graph Representations

This work provides the first unifying theoretical framework for node embeddings and structural graph representations, bridging methods like matrix factorization and graph neural networks, and introduces new practical guidelines to generating and using nodeembeddings, which fixes significant shortcomings of standard operating procedures used today.

Labeled Graph Generative Adversarial Networks

This work proposes labeled-graph generative adversarial networks (LGGAN) to train deep generative models for graph-structured data with node labels and test the approach on various types of graph datasets, such as collections of citation networks and protein graphs.

Web Text Categorization: A LSTM-RNN Approach

A long-short-term memory (LSTM) recurrent neural network (RNN) based system along with handcrafted graph-based features is proposed for text categorization that represents each document by a weighted graph for determining the relationships among the tokens.

Spruce Snowshoe Hare Red Squirrel Lynx Coyote Red Fox Ground Squirrel Zooplankton Krill Pelagic Fish Orca Seal Baleen Whale

  • Computer Science
  • 2019
This work provides the first unifying theoretical framework for node (positional) embeddings and structural graph representations, bridging methods like matrix factorization and graph neural networks and introduces new practical guidelines to generating and using node embeddins, which fixes significant shortcomings of standard operating procedures used today.

Tweet-scan-post: a system for analysis of sensitive private data disclosure in online social media

This research work aims to define the user entities or data like phone number, email address, family details, health-related information as user’s sensitive private data (SPD) in a social media platform and proposes a novel layered classification approach with various state-of-art machine learning models to classify tweets as sensitive and insensitive.

Deep Representation Learning on Labeled Graphs

References

SHOWING 1-10 OF 33 REFERENCES

Training Iterative Collective Classifiers with BackPropagation

This paper introduces a variant of ICA, ICA with back-propagation (BPICA) as a procedure analogous to recurrent neural network prediction, which enables gradient-based strategies for optimizing over model parameters.

Deep Collective Inference

This paper develops a collective inference method, which is referred to as Deep Collective Inference (DCI), that uses semi-supervised learning in partially-labeled networks and two label distribution correction mechanisms for imbalanced classes and compares to several alternative methods on seven network datasets.

Column Networks for Collective Classification

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

Cautious Inference in Collective Classification

It is conjecture that cautious approaches that identify and preferentially exploit the more reliable intermediate data should outperform aggressive approaches and is explained why caution is useful and introduced three parameters to control the degree of caution.

Discriminative Probabilistic Models for Relational Data

An alternative framework that builds on (conditional) Markov networks and addresses two limitations of the previous approach is presented, showing how to train these models effectively, and how to use approximate probabilistic inference over the learned model for collective classification of multiple related entities.

Multi-Label Collective Classification

Empirical studies on real-world tasks demonstrate that the proposed Icml (Iterative Classification of Multiple Labels), to effectively assign a set of multiple labels to each instance in the relational dataset, can effectively boost classification performances in multilabel relational datasets.

Combining Collective Classification and Link Prediction

This paper investigates empirically the conditions under which an integrated approach to object classification and link prediction improves performance, and finds that performance improves over a wide range of network types, and algorithm settings.

Why collective inference improves relational classification

This work describes the necessary and sufficient conditions for reduced classification error based on experiments with real and simulated data, and characterizes different types of statistical models used for making inference in relational data.

Collective Classification in Network Data

This article introduces four of the most widely used inference algorithms for classifying networked data and empirically compare them on both synthetic and real-world data.

Iterative Classification in Relational Data

An iterative classification approach that uses simple Bayesian classifiers in an iterative fashion, dynamically upd ating the attributes of some objects as inferences are made about related ob jects.