Adversarial Context Aware Network Embeddings for Textual Networks
- URL: http://arxiv.org/abs/2011.02665v1
- Date: Thu, 5 Nov 2020 05:20:01 GMT
- Title: Adversarial Context Aware Network Embeddings for Textual Networks
- Authors: Tony Gracious, Ambedkar Dukkipati
- Abstract summary: Existing approaches learn embeddings of text and network structure by enforcing embeddings of connected nodes to be similar.
This implies that these approaches require edge information for learning embeddings and they cannot learn embeddings of unseen nodes.
We propose an approach that achieves both modality fusion and the capability to learn embeddings of unseen nodes.
- Score: 8.680676599607123
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Representation learning of textual networks poses a significant challenge as
it involves capturing amalgamated information from two modalities: (i)
underlying network structure, and (ii) node textual attributes. For this, most
existing approaches learn embeddings of text and network structure by enforcing
embeddings of connected nodes to be similar. Then for achieving a modality
fusion they use the similarities between text embedding of a node with the
structure embedding of its connected node and vice versa. This implies that
these approaches require edge information for learning embeddings and they
cannot learn embeddings of unseen nodes. In this paper we propose an approach
that achieves both modality fusion and the capability to learn embeddings of
unseen nodes. The main feature of our model is that it uses an adversarial
mechanism between text embedding based discriminator, and structure embedding
based generator to learn efficient representations. Then for learning
embeddings of unseen nodes, we use the supervision provided by the text
embedding based discriminator. In addition this, we propose a novel
architecture for learning text embedding that can combine both mutual attention
and topological attention mechanism, which give more flexible text embeddings.
Through extensive experiments on real-world datasets, we demonstrate that our
model makes substantial gains over several state-of-the-art benchmarks. In
comparison with previous state-of-the-art, it gives up to 7% improvement in
performance in predicting links among nodes seen in the training and up to 12%
improvement in performance in predicting links involving nodes not seen in
training. Further, in the node classification task, it gives up to 2%
improvement in performance.
Related papers
- Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models [31.443478448031886]
RoSE (Relation-oriented Semantic Edge-decomposition) is a novel framework that decomposes the graph structure by analyzing raw text attributes.
Our framework significantly enhances node classification performance across various datasets, with improvements of up to 16% on the Wisconsin dataset.
arXiv Detail & Related papers (2024-05-28T20:54:47Z) - TeKo: Text-Rich Graph Neural Networks with External Knowledge [75.91477450060808]
We propose a novel text-rich graph neural network with external knowledge (TeKo)
We first present a flexible heterogeneous semantic network that incorporates high-quality entities.
We then introduce two types of external knowledge, that is, structured triplets and unstructured entity description.
arXiv Detail & Related papers (2022-06-15T02:33:10Z) - Link Prediction with Contextualized Self-Supervision [63.25455976593081]
Link prediction aims to infer the existence of a link between two nodes in a network.
Traditional link prediction algorithms are hindered by three major challenges -- link sparsity, node attribute noise and network dynamics.
We propose a Contextualized Self-Supervised Learning framework that fully exploits structural context prediction for link prediction.
arXiv Detail & Related papers (2022-01-25T03:12:32Z) - Temporal Graph Network Embedding with Causal Anonymous Walks
Representations [54.05212871508062]
We propose a novel approach for dynamic network representation learning based on Temporal Graph Network.
For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings.
We show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks.
arXiv Detail & Related papers (2021-08-19T15:39:52Z) - Variational Co-embedding Learning for Attributed Network Clustering [30.7006907516984]
Recent works for attributed network clustering utilize graph convolution to obtain node embeddings and simultaneously perform clustering assignments on the embedding space.
We propose a variational co-embedding learning model for attributed network clustering (ANC)
ANC is composed of dual variational auto-encoders to simultaneously embed nodes and attributes.
arXiv Detail & Related papers (2021-04-15T08:11:47Z) - Node2Seq: Towards Trainable Convolutions in Graph Neural Networks [59.378148590027735]
We propose a graph network layer, known as Node2Seq, to learn node embeddings with explicitly trainable weights for different neighboring nodes.
For a target node, our method sorts its neighboring nodes via attention mechanism and then employs 1D convolutional neural networks (CNNs) to enable explicit weights for information aggregation.
In addition, we propose to incorporate non-local information for feature learning in an adaptive manner based on the attention scores.
arXiv Detail & Related papers (2021-01-06T03:05:37Z) - GAGE: Geometry Preserving Attributed Graph Embeddings [34.25102483600248]
This paper presents a novel approach for node embedding in attributed networks.
It preserves the distances of both the connections and the attributes.
An effective and lightweight algorithm is developed to tackle the learning task.
arXiv Detail & Related papers (2020-11-03T02:07:02Z) - DINE: A Framework for Deep Incomplete Network Embedding [33.97952453310253]
We propose a Deep Incomplete Network Embedding method, namely DINE.
We first complete the missing part including both nodes and edges in a partially observable network by using the expectation-maximization framework.
We evaluate DINE over three networks on multi-label classification and link prediction tasks.
arXiv Detail & Related papers (2020-08-09T04:59:35Z) - Unsupervised Differentiable Multi-aspect Network Embedding [52.981277420394846]
We propose a novel end-to-end framework for multi-aspect network embedding, called asp2vec.
Our proposed framework can be readily extended to heterogeneous networks.
arXiv Detail & Related papers (2020-06-07T19:26:20Z) - Exploiting Structured Knowledge in Text via Graph-Guided Representation
Learning [73.0598186896953]
We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs.
Building upon entity-level masked language models, our first contribution is an entity masking scheme.
In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training.
arXiv Detail & Related papers (2020-04-29T14:22:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.