Eric Inae
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Eric Inae has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Gang Liu
University of Notre Dame, Notre Dame, IN, USA
3 shared publications - Meng Jiang
University of Notre Dame
3 shared publications - Tengfei Luo
Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, USA
3 shared publications - Jiaxin Xu
Department of Aerospace and Mechanical Engineering, University of Notre Dame, Notre Dame, IN, 46556, USA
1 shared publication - Renzheng Zhang
University of Notre Dame
1 shared publication - Tong Zhao
Snap Inc., Bellevue, WA, USA
1 shared publication
Latest Publications
- Open Access
- 13 February 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (4) , 1-23
Rationalizing Graph Neural Networks with Data Augmentation
Graph rationales are representative subgraph structures that best explain and support the graph neural network (GNN) predictions. Graph rationalization involves the joint identification of these subgraphs during GNN training, resulting in improved interpretability and generalization. GNN is widely used for node-level tasks such as paper classification and graph-level tasks such as molecular property prediction. However, on both levels, little attention has been given to GNN rationalization and the lack of training examples makes it difficult to identify the optimal graph rationales. In this work, we address the problem by proposing a unified data augmentation framework with two novel operations on environment subgraphs to rationalize GNN prediction. We define the environment subgraph as the remaining subgraph after rationale identification and separation. The framework efficiently performs rationale–environment separation in therepresentation spacefor a node’s neighborhood graph or a graph’s complete structure to avoid the high complexity of explicit graph decoding and encoding. We conduct experiments on 17 datasets spanning node classification, graph classification, and graph regression. Results demonstrate that our framework is effective and efficient in rationalizing and enhancing GNNs for different levels of tasks on graphs.
- 13 February 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (4) , 1-23
Open AccessRationalizing Graph Neural Networks with Data Augmentation
Graph rationales are representative subgraph structures that best explain and support the graph neural network (GNN) predictions. Graph rationalization involves the joint identification of these subgraphs during GNN training, resulting in improved interpretability and generalization. GNN is widely used for node-level tasks such as paper classification and graph-level tasks such as molecular property prediction. However, on both levels, little attention has been given to GNN rationalization and the lack of training examples makes it difficult to identify the optimal graph rationales. In this work, we address the problem by proposing a unified data augmentation framework with two novel operations on environment subgraphs to rationalize GNN prediction. We define the environment subgraph as the remaining subgraph after rationale identification and separation. The framework efficiently performs rationale–environment separation in therepresentation spacefor a node’s neighborhood graph or a graph’s complete structure to avoid the high complexity of explicit graph decoding and encoding. We conduct experiments on 17 datasets spanning node classification, graph classification, and graph regression. Results demonstrate that our framework is effective and efficient in rationalizing and enhancing GNNs for different levels of tasks on graphs.
- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1453-1465
Semi-Supervised Graph Imbalanced Regression
Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph datasets are often small because labeling them requires expensive equipment and effort. To address the lack of examples of rare label values in graph regression tasks, we propose a semi-supervised framework to progressively balance training data and reduce model bias via self-training. The training data balance is achieved by (1) pseudo-labeling more graphs for under-represented labels with a novel regression confidence measurement and (2) augmenting graph examples in latent space for remaining rare labels after data balancing with pseudo-labels. The former is to identify quality examples from unlabeled data whose labels are confidently predicted and sample a subset of them with a reverse distribution from the imbalanced annotated data. The latter collaborates with the former to target a perfect balance using a novel label-anchored mixup algorithm. We perform experiments in seven regression tasks on graph datasets. Results demonstrate that the proposed framework significantly reduces the error of predicted graph properties, especially in under-represented label areas.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 1453-1465
Open AccessSemi-Supervised Graph Imbalanced Regression
Data imbalance is easily found in annotated data when the observations of certain continuous label values are difficult to collect for regression tasks. When they come to molecule and polymer property predictions, the annotated graph datasets are often small because labeling them requires expensive equipment and effort. To address the lack of examples of rare label values in graph regression tasks, we propose a semi-supervised framework to progressively balance training data and reduce model bias via self-training. The training data balance is achieved by (1) pseudo-labeling more graphs for under-represented labels with a novel regression confidence measurement and (2) augmenting graph examples in latent space for remaining rare labels after data balancing with pseudo-labels. The former is to identify quality examples from unlabeled data whose labels are confidently predicted and sample a subset of them with a reverse distribution from the imbalanced annotated data. The latter collaborates with the former to target a perfect balance using a novel label-anchored mixup algorithm. We perform experiments in seven regression tasks on graph datasets. Results demonstrate that the proposed framework significantly reduces the error of predicted graph properties, especially in under-represented label areas.