Data Augmentation for Graph Neural Networks
- Tong Zhao, Yozen Liu, Leonardo Neves, Oliver J. Woodford, Meng Jiang, Neil Shah
- Computer ScienceAAAI Conference on Artificial Intelligence
- 11 June 2020
This work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra- class edges and demote inter-class edges in given graph structure, and introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction.
Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
- Shichang Zhang, Yozen Liu, Yizhou Sun, Neil Shah
- Computer ScienceInternational Conference on Learning…
- 17 October 2021
Comprehensive analysis shows when and why GLNNs can achieve competitive accuracies to GNNs and suggests GLNN as a handy choice for latency-constrained applications.
A Unified View on Graph Neural Networks as Graph Signal Denoising
- Yao Ma, Xiaorui Liu, Tong Zhao, Yozen Liu, Jiliang Tang, Neil Shah
- Computer ScienceInternational Conference on Information and…
- 5 October 2020
It is established mathematically that the aggregation processes in a group of representative GNN models including GCN, GAT, PPNP, and APPNP can be regarded as solving a graph denoising problem with a smoothness assumption.
Characterizing and Forecasting User Engagement with In-App Action Graph: A Case Study of Snapchat
- Yozen Liu, Xiaolin Shi, Lucas Pierce, Xiang Ren
- Computer ScienceKnowledge Discovery and Data Mining
- 2 June 2019
This paper proposes to formalize individual user's in-app action transition patterns as a temporally evolving action graph, and analyze its characteristics in terms of informing future user engagement, and designs an end-to-end, multi-channel neural model to encode both temporal action graphs, activity sequences, and other macroscopic features.
Knowing your FATE: Friendship, Action and Temporal Explanations for User Engagement Prediction on Social Apps
- Xianfeng Tang, Yozen Liu, Neil Shah, Xiaolin Shi, P. Mitra, Suhang Wang
- Computer ScienceKnowledge Discovery and Data Mining
- 10 June 2020
An end-to-end neural framework, FATE, is designed, which incorporates three key factors that are identified to influence user engagement, namely friendships, user actions, and temporal dynamics to achieve explainable engagement predictions.
Graph Neural Networks for Friend Ranking in Large-scale Social Platforms
- Aravind Sankar, Yozen Liu, Jun Yu, Neil Shah
- Computer ScienceThe Web Conference
- 19 April 2021
This work designs a neural architecture GraFRank to learn expressive user representations from multiple feature modalities and user-user interactions, and employs modality-specific neighbor aggregators and cross-modality attentions to learn multi-faceted user representations.
Graph Condensation for Graph Neural Networks
- Wei Jin, Lingxiao Zhao, Shichang Zhang, Yozen Liu, Jiliang Tang, Neil Shah
- Computer ScienceInternational Conference on Learning…
- 14 October 2021
The problem of graph condensation for graph neural networks (GNNs) is proposed and study, aiming to condense the large, original graph into a small, synthetic and highly-informative graph, such that GNNs trained on the small graph and large graph have comparable performance.
Linkless Link Prediction via Relational Distillation
- Zhichun Guo, William Shiao, Tong Zhao
- Computer ScienceArXiv
- 11 October 2022
This work proposes a relational KD framework, Linkless Link Prediction (LLP), which boosts the link prediction performance of MLPs with significant margins, and even outperforms the teacher GNNs on 6 out of 9 benchmarks.
AdverTiming Matters: Examining User Ad Consumption for Effective Ad Allocations on Social Media
- Koustuv Saha, Yozen Liu, M. Bos
- BusinessInternational Conference on Human Factors in…
- 6 May 2021
In a quasi-experimental study on a three-month longitudinal dataset of 100K Snapchat users, it is found ad timing influences ad effectiveness, and insights are drawn on the relationship between ad effectiveness and momentary behaviors such as duration, interactivity, and interaction diversity.
Friend Story Ranking with Edge-Contextual Local Graph Convolutions
- Xianfeng Tang, Yozen Liu, Xinran He, Suhang Wang, Neil Shah
- Computer ScienceWeb Search and Data Mining
- 11 February 2022
This work proposes ELR, an edge-contextual approach which carefully considers local graph structure, differences between local edge types and directionality, and rich edge attributes, building on the backbone of graph convolutions, and handles social sparsity challenges by considering and attending over neighboring nodes, and incorporating multiple edge types in local surrounding egonet structures.
...
...