Over-Smoothing Algorithm and Its Application to GCN Semi-supervised Classification

Dai, Mingzhi; Guo, Wenzhong; Feng, Xiang

doi:10.1007/978-981-15-7984-4_16

Cited by 5 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The best f1 score (0.62) is achieved with the Random Forest algorithm. The traditional models outperform GCN (f1 score of 0.46), and the main cause of this may lie in over-smoothing (Dai, Guo, and Feng 2020). This refers to a situation where, during the training process, the node representations become too similar or indistinguishable across different nodes in the graph.…”

Section: Models Performancementioning

confidence: 99%

Understanding and Improving Content Moderation in Web3 Platforms

Zuo,

Mondragon,

Raman

et al. 2024

ICWSM

View full text Add to dashboard Cite

There have been numerous recent attempts to “decentralize” social media platforms, loosely referred to as Web3. Such ideas, often underpinned by blockchain solutions, offer decentralized equivalents of well-known services (e.g., forums, social networks, video sharing sites, microblogs). One particularly challenging function to implement in such a design is content moderation, due to the lack of central control. Consequently, they often rely on user-controlled moderation, whereby each user must create their own personal block list to filter out content they do not wish to see. This paper presents a first study of user-controlled moderation on one exemplar Web3 social microblogging platform called memo.cash. Based on a dataset covering 391K posts, we study the factors that lead users to “mute” each other. We find that the most crucial factor is the platform action count, rather than the presence of things like hate speech. We also show that the followership network plays a pivotal role in determining their visibility on the platform, further influencing their muting behavior. This leads us to design tooling to automate the muting process on a per-user basis. We model this as a recommendation problem, and experiment with a number of state-of-the-art recommender engines. We show that our system can generate effective personalized mute lists for users.

show abstract

Section: Models Performancementioning

confidence: 99%