Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs

Rózemberczki, Benedek; Kiss, Oliver; Sarkar, Rik

doi:10.48550/arxiv.2003.04819

Cited by 4 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is achieved by learning a mapping function between a vertex attribute vector and a role, represented by vertex connectivity patterns, such that two vertices belong to the same role if they are structurally similar or equivalent. The embeddings have been computed using the karateclub [34] Python library. The network embeddings are trained using the hyperparameter configuration of the package shown in Table 2.…”

Section: Network Embeddingsmentioning

confidence: 99%

Introducing Various Semantic Models for Amharic: Experimentation and Evaluation with Multiple Tasks and Datasets

et al. 2021

View full text Add to dashboard Cite

The availability of different pre-trained semantic models has enabled the quick development of machine learning components for downstream applications. However, even if texts are abundant for low-resource languages, there are very few semantic models publicly available. Most of the publicly available pre-trained models are usually built as a multilingual version of semantic models that will not fit well with the need for low-resource languages. We introduce different semantic models for Amharic, a morphologically complex Ethio-Semitic language. After we investigate the publicly available pre-trained semantic models, we fine-tune two pre-trained models and train seven new different models. The models include Word2Vec embeddings, distributional thesaurus (DT), BERT-like contextual embeddings, and DT embeddings obtained via network embedding algorithms. Moreover, we employ these models for different NLP tasks and study their impact. We find that newly-trained models perform better than pre-trained multilingual models. Furthermore, models based on contextual embeddings from FLAIR and RoBERTa perform better than word2Vec models for the NER and POS tagging tasks. DT-based network embeddings are suitable for the sentiment classification task. We publicly release all the semantic models, machine learning components, and several benchmark datasets such as NER, POS tagging, sentiment classification, as well as Amharic versions of WordSim353 and SimLex999.

show abstract

Section: Network Embeddingsmentioning

confidence: 99%

Introducing Various Semantic Models for Amharic: Experimentation and Evaluation with Multiple Tasks and Datasets

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Such structures can also be found in the legal citation graph in the form of different topics or jurisdictions. For DeepWalk, Walklets, BoostNe, we use the Karate Club implementation [45].…”

Section: 24mentioning

confidence: 99%

Evaluating Document Representations for Content-based Legal Literature Recommendations

Ostendorff¹,

Ash²,

Ruas³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recommender systems assist legal professionals in finding relevant literature for supporting their case. Despite its importance for the profession, legal applications do not reflect the latest advances in recommender systems and representation learning research. Simultaneously, legal recommender systems are typically evaluated in small-scale user study without any public available benchmark datasets. Thus, these studies have limited reproducibility. To address the gap between research and practice, we explore a set of state-ofthe-art document representation methods for the task of retrieving semantically related US case law. We evaluate text-based (e.g., fast-Text, Transformers), citation-based (e.g., DeepWalk, Poincaré), and hybrid methods. We compare in total 27 methods using two silver standards with annotations for 2,964 documents. The silver standards are newly created from Open Case Book and Wikisource and can be reused under an open license facilitating reproducibility. Our experiments show that document representations from averaged fast-Text word vectors (trained on legal corpora) yield the best results, closely followed by Poincaré citation embeddings. Combining fast-Text and Poincaré in a hybrid manner further improves the overall result. Besides the overall performance, we analyze the methods depending on document length, citation count, and the coverage of their recommendations. We make our source code, models, and datasets publicly available.

show abstract

“…Data. Our experiments are carried out using the datasets DBLP_v1 Pan et al [2013], IMDB-MULTI Yanardag and Vishwanathan [2015], and deezer_ego_nets Rozemberczki et al [2020] from the TUD graph benchmark database Morris et al [2020]. Graphs whose maximum clique contained less than 3 nodes were excluded, and for the deezer_ego_nets, we excluded those graphs that had more than 30 nodes, giving the dataset statistics shown in Table 1.…”

Section: Experiments and Evaluationmentioning

confidence: 99%

Graph2Graph Learning with Conditional Autoregressive Models

Wang,

Lauze,

Feragen

2021

Preprint

View full text Add to dashboard Cite

We present a graph neural network model for solving graph-to-graph learning problems. Most deep learning on graphs considers "simple" problems such as graph classification or regressing real-valued graph properties. For such tasks, the main requirement for intermediate representations of the data is to maintain the structure needed for output, i.e. keeping classes separated or maintaining the order indicated by the regressor. However, a number of learning tasks, such as regressing graph-valued output, generative models, or graph autoencoders, aim to predict a graph-structured output. In order to successfully do this, the learned representations need to preserve far more structure. We present a conditional auto-regressive model for graph-to-graph learning and illustrate its representational capabilities via experiments on challenging subgraph predictions from graph algorithmics; as a graph autoencoder for reconstruction and visualization; and on pretraining representations that allow graph classification with limited labeled data.Preprint. Under review.

show abstract

Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs

Cited by 4 publications

References 22 publications

Introducing Various Semantic Models for Amharic: Experimentation and Evaluation with Multiple Tasks and Datasets

Introducing Various Semantic Models for Amharic: Experimentation and Evaluation with Multiple Tasks and Datasets

Evaluating Document Representations for Content-based Legal Literature Recommendations

Graph2Graph Learning with Conditional Autoregressive Models

Contact Info

Product

Resources

About