Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
Apr 17, 2020 · Specifically, we propose to apply a bottom-up pooling layer to enlarge the receptive field of each node, then use a top-down unpooling layer to ...
We analyze why this may hinder the performance of graph pooling, then propose a novel graph pooling method called Bottom-Up and Top-Down graph POOLing (BUTDPool) ...
People also ask
May 11, 2020 · BUTDPool aims to learn a more fine-grained pooling criterion based on coarse global structure information produced by a bottom-up pooling layer, ...
BUTDPool aims to learn a more fine-grained pooling criterion based on coarse global structure information produced by a bottom-up pooling layer, and can enhance ...
A curated list of papers on graph pooling (More than 150 papers reviewed). We provide a taxonomy of existing papers as shown in the above figure.
Bottom-Up and Top-Down Graph Pooling. Published on Oct 14, 202010 Views. Jia-Qi Yang · PAKDD 2020 - Singapore. Bookmark You need to login
May 18, 2024 · With the module identification, MGPool goes through three stages from bottom to top: node, module and graph to form the graph embedding. •. In ...
Missing: Up Down
Jun 13, 2024 · This benchmark systematically assesses the performance of graph pooling methods in three dimensions, ie, effectiveness, robustness, and generalizability.
As an es- sential component of the architecture, graph pool- ing is indispensable for obtaining a holistic graph- level representation of the whole graph.
Missing: Bottom- | Show results with:Bottom-
Sep 29, 2021 · We propose a new plug-and-play pooling module, termed as Distribution Knowledge Embedding (DKEPool), where graphs are rephrased as distributions on top of GNNs.