Notices by arXiv Computer Science (arxivcs@qoto.org)

arXiv Computer Science (arxivcs@qoto.org)'s status on Friday, 20-Dec-2019 03:00:11 UTC arXiv Computer Science

Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection. (arXiv:1912.08808v1 [cs.SI]) http://arxiv.org/abs/1912.08808
In conversation Friday, 20-Dec-2019 03:00:11 UTC from qoto.org permalink
Attachments
1. Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection
  
  Graph embedding has become a key component of many data mining and analysis systems. Current graph embedding approaches either sample a large number of node pairs from a graph to learn node embeddings via stochastic optimization or factorize a high-order proximity/adjacency matrix of the graph via computationally expensive matrix factorization techniques. These approaches typically require significant resources for the learning process and rely on multiple parameters, which limits their applicability in practice. Moreover, most of the existing graph embedding techniques operate effectively in one specific metric space only (e.g., the one produced with cosine similarity), do not preserve higher-order structural features of the input graph and cannot automatically determine a meaningful number of embedding dimensions. Typically, the produced embeddings are not easily interpretable, which complicates further analyses and limits their applicability. To address these issues, we propose DAOR, a highly efficient and parameter-free graph embedding technique producing metric space-robust, compact and interpretable embeddings without any manual tuning. Compared to a dozen state-of-the-art graph embedding algorithms, DAOR yields competitive results on both node classification (which benefits form high-order proximity) and link prediction (which relies on low-order proximity mostly). Unlike existing techniques, however, DAOR does not require any parameter tuning and improves the embeddings generation speed by several orders of magnitude. Our approach has hence the ambition to greatly simplify and speed up data analysis tasks involving graph representation learning.
arXiv Computer Science (arxivcs@qoto.org)'s status on Wednesday, 04-Sep-2019 03:00:10 UTC arXiv Computer Science

A single-layer RNN can approximate stacked and bidirectional RNNs, and topologies in between. (arXiv:1909.00021v1 [cs.LG]) http://arxiv.org/abs/1909.00021
In conversation Wednesday, 04-Sep-2019 03:00:10 UTC from qoto.org permalink
Attachments
1. A single-layer RNN can approximate stacked and bidirectional RNNs, and topologies in between
arXiv Computer Science (arxivcs@qoto.org)'s status on Tuesday, 21-Aug-2018 00:46:04 UTC arXiv Computer Science

Heuristics for publishing dynamic content as structured data with schema.org. (arXiv:1808.06012v1 [cs.IR]) http://arxiv.org/abs/1808.06012
In conversation Tuesday, 21-Aug-2018 00:46:04 UTC from qoto.org permalink
Attachments
1. Untitled attachment
arXiv Computer Science (arxivcs@qoto.org)'s status on Monday, 20-Aug-2018 00:31:04 UTC arXiv Computer Science

Predicting Human Trustfulness from Facebook Language. (arXiv:1808.05668v1 [cs.CL]) http://arxiv.org/abs/1808.05668
In conversation Monday, 20-Aug-2018 00:31:04 UTC from qoto.org permalink
Attachments
1. Untitled attachment
arXiv Computer Science (arxivcs@qoto.org)'s status on Thursday, 16-Aug-2018 00:31:07 UTC arXiv Computer Science

VizML: A Machine Learning Approach to Visualization Recommendation. (arXiv:1808.04819v1 [cs.HC]) http://arxiv.org/abs/1808.04819
In conversation Thursday, 16-Aug-2018 00:31:07 UTC from qoto.org permalink
Attachments
1. Untitled attachment
arXiv Computer Science (arxivcs@qoto.org)'s status on Tuesday, 31-Jul-2018 00:51:06 UTC arXiv Computer Science

NDBench: Benchmarking Microservices at Scale. (arXiv:1807.10792v1 [cs.DB]) http://arxiv.org/abs/1807.10792
In conversation Tuesday, 31-Jul-2018 00:51:06 UTC from qoto.org permalink
Attachments
1. Untitled attachment
arXiv Computer Science (arxivcs@qoto.org)'s status on Monday, 16-Jul-2018 00:31:06 UTC arXiv Computer Science

Improving on Q & A Recurrent Neural Networks Using Noun-Tagging. (arXiv:1807.04778v1 [cs.LG]) http://arxiv.org/abs/1807.04778
In conversation Monday, 16-Jul-2018 00:31:06 UTC from qoto.org permalink
Attachments
1. Untitled attachment

Public

Notices by arXiv Computer Science (arxivcs@qoto.org)

User actions

Following 0

Followers 0

Groups 0

Statistics

Feeds