Share This Author
How Powerful are Graph Neural Networks?
This work characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures, and develops a simple architecture that is provably the most expressive among the class of GNNs.
Co-teaching: Robust training of deep neural networks with extremely noisy labels
Empirical results on noisy versions of MNIST, CIFar-10 and CIFAR-100 demonstrate that Co-teaching is much superior to the state-of-the-art methods in the robustness of trained deep models.
Open Graph Benchmark: Datasets for Machine Learning on Graphs
The OGB datasets are large-scale, encompass multiple important graph ML tasks, and cover a diverse range of domains, ranging from social and information networks to biological networks, molecular graphs, source code ASTs, and knowledge graphs, indicating fruitful opportunities for future research.
Strategies for Pre-training Graph Neural Networks
A new strategy and self-supervised methods for pre-training Graph Neural Networks (GNNs) that avoids negative transfer and improves generalization significantly across downstream tasks, leading up to 9.4% absolute improvements in ROC-AUC over non-pre-trained models and achieving state-of-the-art performance for molecular property prediction and protein function prediction.
Learning Discrete Representations via Information Maximizing Self-Augmented Training
- Weihua Hu, Takeru Miyato, Seiya Tokui, Eiichi Matsumoto, Masashi Sugiyama
- Computer ScienceICML
- 28 February 2017
In IMSAT, data augmentation is used to impose the invari-ance on discrete representations and the predicted representations of augmented data points to be close to those of the original data points in an end-to-end fashion to maximize the information-theoretic dependency between data and their predicted discrete representations.
OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
- Weihua Hu, Matthias Fey, Hongyu Ren, Maho Nakata, Yuxiao Dong, J. Leskovec
- Computer ScienceNeurIPS Datasets and Benchmarks
- 17 March 2021
It is shown that expressive models signiﬁcantly outperform simple scalable baselines, indicating an opportunity for dedicated efforts to further improve graph ML at scale.
Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
Answering complex logical queries on large-scale incomplete knowledge graphs (KGs) is a fundamental yet challenging task. Recently, a promising approach to this problem has been to embed KG entities…
Does Distributionally Robust Supervised Learning Give Robust Classifiers?
This paper proves that the DRSL just ends up giving a classifier that exactly fits the given training distribution, which is too pessimistic, and proposes simple D RSL that overcomes this pessimism and empirically demonstrate its effectiveness.
Learning from Complementary Labels
This paper shows that an unbiased estimator to the classification risk can be obtained only from complementarily labeled data, if a loss function satisfies a particular symmetric condition, and derives estimation error bounds and proves that the optimal parametric convergence rate is achieved.
The Open Catalyst 2020 (OC20) Dataset and Community Challenges
- L. Chanussot, Abhishek Das, Zachary W. Ulissi
- Environmental ScienceProceedings of the International Conference on…
- 20 October 2020
The OC20 dataset is developed, consisting of 1,281,121 Density Functional Theory relaxations across a wide swath of materials, surfaces, and adsorbates, and three state-of-the-art graph neural network models were applied to each of these tasks as baseline demonstrations for the community to build on.