While generating better negative samples for contrastive learning has been widely studied in the areas of CV and NLP, very few work has focused on graph-structured data. Recently, Mixup has been introduced to synthesize hard negative samples in graph contrastive learning (GCL). However, due to the unsupervised learning nature of GCL, without the help of soft labels, directly mixing representations of samples could inadvertently lead to the information loss of the original hard negative and further adversely affect the quality of the newly generated harder negative. To address the problem, in this paper, we propose a novel method DropMix to synthesize harder negative samples, which consists of two main steps. Specifically, we first select some hard negative samples by measuring their hardness from both local and global views in the graph simultaneously. After that, we mix hard negatives only on partial representation dimensions to generate harder ones and decrease the information loss caused by Mixup. We conduct extensive experiments to verify the effectiveness of DropMix on six benchmark datasets. Our results show that our method can lead to better GCL performance. Our data and codes are publicly available at https://github.com/Mayueq/DropMix-Code.

Mixed sample data augmentation (MSDA) is a widely used technique that has been found to improve performance in a variety of tasks. However, in this paper, we show that the effects of MSDA are class-dependent, with some classes seeing an improvement in performance while others experience a decline. To reduce class dependency, we propose the DropMix method, which excludes a specific percentage of data from the MSDA computation. By training on a combination of MSDA and non-MSDA data, the proposed method not only improves the performance of classes that were previously degraded by MSDA, but also increases overall average accuracy, as shown in experiments on two datasets (CIFAR-100 and ImageNet) using three MSDA methods (Mixup, CutMix and PuzzleMix).

Ever wanted to combine the vocals from "Call Me Maybe" with the guitar from The Jackson 5's "I Want You Back"? With a new game, Boston-based music video game giant Harmonix -- makers of the iconic Rock Band franchise -- you can add these two songs, and hopefully better combinations, together, to make your own mash-ups using a smartphone, a high-tech gameboard and deck of cards. "There's a feeling you get when you hold the cards in your hand and slap it down on the board, you transform into a music maker, you feel like a DJ," said Steve Janiak, Harmonix' chief executive, during an interview at PAX East last night. "You're in control of the mix in a way you wouldn't feel if you were just doing it on a screen." The new game, Dropmix, lets players combine the vocals of one song with the bass line from another and add the drums from a third song to make an entirely new tune. When it is released later this year, the game will include current hits from Bruno Mars, The Chainsmokers and Ed Sheeran, as well as classics like The Jackson 5, Run-D.M.C and Barbra Streisand.