Search
M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search
Yelong Shen, Jianshu Chen, Po-Sen Huang, Yuqing Guo, Jianfeng Gao
Neural Information Processing Systems http://nips.cc/
state-of-the-art is a recent 0.401
In the last few years, the ability to effectively summarize data has gained importance due to the advent of massive datasets in many fields.
Exact Combinatorial Optimization with Graph Convolutional Neural Networks
Maxime Gasse, Didier Chetelat, Nicola Ferroni, Laurent Charlin, Andrea Lodi
In practice, most combinatorial optimization problems can be formulated as mixed-integer linear programs (MILPs), in which case branch-and-bound (B&B) [35] is the exact method of choice.
Norm-Ranging LSH for Maximum Inner Product Search
Xiao Yan, Jinfeng Li, Xinyan Dai, Hongzhi Chen, James Cheng
MIPS is a challenging problem as modern datasets often have high dimensionality and large cardinality. Initially, tree-based methods [Ram and Gray, 2012, Koenigstein et al., 2012] were proposed for MIPS, which use the idea of branch and bound similar to k-d tree [Friedman and Tukey, 1974].
NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA (Supplement)
The initial learning rate is set to 0.0005 with an exponential learning rate scheduler with a decay rate of 0.99. Also, we use the KL divergence as the loss function.
LearningBeamSearchPoliciesviaImitation Learning
Beam search is widely used for approximate decoding in structured prediction problems. Models often use a beam at test time but ignore its existence at train time, and therefore do not explicitly learn how to use the beam.