Line Graph Neural Networks for Link Prediction
نویسندگان
چکیده
منابع مشابه
Link Prediction Based on Graph Neural Networks
Traditional methods for link prediction can be categorized into three main types: graph structure feature-based, latent feature-based, and explicit feature-based. Graph structure feature methods leverage some handcrafted node proximity scores, e.g., common neighbors, to estimate the likelihood of links. Latent feature methods rely on factorizing networks’ matrix representations to learn an embe...
متن کاملpresenting a new method for link prediction in social networks
today, online social networks are very popular due to the possibility of creating relationships between people all over the world. these social networks with possibilities such as friend recommendation generally use local features derived from social graph structure. for friend recommendation, there are different algorithms with local and global approaches. in this paper, we proposed an algorit...
متن کاملLink Scheduling in STDMA Wireless Networks: A Line Graph Approach
We consider point to point link scheduling in Spatial Time Division Multiple Access (STDMA) wireless networks under the physical interference model. We propose a novel link scheduling algorithm based on a line graph representation of the network, by embedding the interferences between pairs of nodes into the edge weights of the line graph. Our algorithm achieves lower schedule length and lower ...
متن کاملGraph Convolutional Neural Networks for ADME Prediction in Drug Discovery
ADME in-silico methods have grown increasingly powerful over the past twenty years, driven by advances in machine learning and the abundance of high-quality training data generated by laboratory automation. Meanwhile, in the technology industry, deep-learning has taken o↵, driven by advances in topology design, computation, and data. The key premise of these methods is that the model is able to...
متن کاملSubgraph Pattern Neural Networks for High-Order Graph Evolution Prediction
In this work we generalize traditional node/link prediction tasks in dynamic heterogeneous networks, to consider joint prediction over larger k-node induced subgraphs. Our key insight is to incorporate the unavoidable dependencies in the training observations of induced subgraphs into both the input features and the model architecture itself via high-order dependencies. The strength of the repr...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Pattern Analysis and Machine Intelligence
سال: 2021
ISSN: 0162-8828,2160-9292,1939-3539
DOI: 10.1109/tpami.2021.3080635