GeomGCL: Geometric Graph Contrastive Learning for Molecular Property Prediction

Graph Memory Networks for Molecular Activity Prediction

Molecular activity prediction is critical in drug design. Machine learning techniques such as kernel methods and random forests have been successful for this task. These models require fixed-size feature vectors as input while the molecules are variable in size and structure. As a result, fixed-size fingerprint representation is poor in handling substructures for large molecules. Here we approa...

Contrastive Learning for Image Captioning

Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of captions, as distinctive captions are more likely to describe images with their unique aspects. In this work, we propose a new learning method, Contrastive Learn...

Selection of Molecular Descriptor Subsets for Property Prediction

On Contrastive Divergence Learning

Maximum-likelihood (ML) learning of Markov random fields is challenging because it requires estimates of averages that have an exponential number of terms. Markov chain Monte Carlo methods typically take a long time to converge on unbiased estimates, but Hinton (2002) showed that if the Markov chain is only run for a few steps, the learning can still work well and it approximately minimizes a d...

Geometric Property ( T )

This paper discusses ‘geometric property (T)’. This is a property of metric spaces introduced in earlier work of the authors for its applications to K-theory. Geometric property (T) is a strong form of ‘expansion property’: in particular for a sequence (Xn) of bounded degree finite graphs, it is strictly stronger than (Xn) being an expander in the sense that the Cheeger constants h(Xn) are boun...