ROSE: Role-based Signed Network Embedding

Javari, Amin; Derr, Tyler; Esmailian, Pouya; Tang, Jiliang; Chang, Kevin Chen-Chuan

doi:10.1145/3366423.3380038

Cited by 28 publications

(18 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We identify the key weakness of existing embedding methods as that they only preserve weak similarity consistency. In particular, signed embedding methods [4,21,22,26,54,57] just ensure signed similarity consistency-positively related pairs are separable from negatively related pairs-for sign prediction. And similarly, unsigned embedding methods [14,20,42] only guarantee the topological similarity consistency-topologically close node pairs are separable from distant pairs-for link prediction.…”

Section: Limitation Of Existing Methodsmentioning

confidence: 99%

“…And similarly, unsigned embedding methods [14,20,42] only guarantee the topological similarity consistency-topologically close node pairs are separable from distant pairs-for link prediction. While positive links are detectable as the intersection of positive and topologically [20]) and (b) signed embedding (ROSE [22]) fail to do so.…”

Section: Limitation Of Existing Methodsmentioning

confidence: 99%

“…• ROSE [22]: Transforms the signed network into an unsigned bipartite one by representing each node multiple times. Embeddings for the unsigned network are generated using a randomwalk based approach and combined into signed embeddings.…”

Section: Experimental Settingsmentioning

confidence: 99%

“…(a) is more polarized than (b) as its link signs are related to the community structurenegative links connecting two polarized communities. in representation learning [22,42] help us to address online polarization? One could argue these methods should be as effective for predicting conflicts as they are for recommending connections and content in social media platforms [13].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Pole

Huang

Silva

Singh

2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

From the 2016 U.S. presidential election to the 2021 Capitol riots to the spread of misinformation related to COVID-19, many have blamed social media for today's deeply divided society. Recent advances in machine learning for signed networks hold the promise to guide small interventions with the goal of reducing polarization in social media. However, existing models are especially ineffective in predicting conflicts (or negative links) among users. This is due to a strong correlation between link signs and the network structure, where negative links between polarized communities are too sparse to be predicted even by state-of-the-art approaches. To address this problem, we first design a partition-agnostic polarization measure for signed graphs based on the signed random-walk and show that many real-world graphs are highly polarized. Then, we propose POLE (POLarized Embedding for signed networks), a signed embedding method for polarized graphs that captures both topological and signed similarities jointly via signed autocovariance. Through extensive experiments, we show that POLE significantly outperforms state-of-the-art methods in signed link prediction, particularly for negative links with gains of up to one order of magnitude. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Social networks.

show abstract

Section: Limitation Of Existing Methodsmentioning

confidence: 99%

Section: Limitation Of Existing Methodsmentioning

confidence: 99%

Section: Experimental Settingsmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Pole

Huang

Silva

Singh

2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…Another relevant question is (Q2) how should random-walk embeddings be used for link prediction? Following node2vec [26], several works train classifiers to predict missing links based on a set of labelled pairs (edges and non-edges) [30,40,62]. This is counter-intuitive given that the embedding problem is often defined in terms of dot products.…”

Section: Introductionmentioning

confidence: 99%

A Broader Picture of Random-walk Based Graph Embedding

Huang

Silva

Singh

2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Graph embedding based on random-walks supports effective solutions for many graph-related downstream tasks. However, the abundance of embedding literature has made it increasingly difficult to compare existing methods and to identify opportunities to advance the state-of-the-art. Meanwhile, existing work has left several fundamental questions-such as how embeddings capture different structural scales and how they should be applied for effective link prediction-unanswered. This paper addresses these challenges with an analytical framework for random-walk based graph embedding that consists of three components: a randomwalk process, a similarity function, and an embedding algorithm. Our framework not only categorizes many existing approaches but naturally motivates new ones. With it, we illustrate novel ways to incorporate embeddings at multiple scales to improve downstream task performance. We also show that embeddings based on autocovariance similarity, when paired with dot product ranking for link prediction, outperform state-of-the-art methods based on Pointwise Mutual Information similarity by up to 100%.

show abstract