Timezone: »
Detecting statistical interactions between input features is a crucial and challenging task. Recent advances demonstrate that it is possible to extract learned interactions from trained neural networks. It has also been observed that, in neural networks, any interacting features must follow a strongly weighted connection to common hidden units. Motivated by the observation, in this paper, we propose to investigate the interaction detection problem from a novel topological perspective by analyzing the connectivity in neural networks. Specially, we propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. Based on this measure, a Persistence Interaction Dection (PID) algorithm is developed to efficiently detect interactions. Our proposed algorithm is evaluated across a number of interaction detection tasks on several synthetic and real-world datasets with different hyperparameters. Experimental results validate that the PID algorithm outperforms the state-of-the-art baselines.
Author Information
Zirui Liu (Texas A&M University)
I am a Ph.D. student in Texas A&M University
Qingquan Song (Texas A&M University)
Kaixiong Zhou (Texas A&M University)
Ting-Hsiang Wang (Texas A&M University)
Ying Shan (Tencent)
Xia Hu (Texas A&M University)
More from the Same Authors
-
2021 : Revisiting Time Series Outlier Detection: Definitions and Benchmarks »
Kwei-Herng Lai · Daochen Zha · Junjie Xu · Yue Zhao · Guanchu Wang · Xia Hu -
2021 Spotlight: Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution »
Liangbin Xie · Xintao Wang · Chao Dong · Zhongang Qi · Ying Shan -
2022 Poster: AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos »
Yanze Wu · Xintao Wang · GEN LI · Ying Shan -
2022 Spotlight: Lightning Talks 5B-3 »
Yanze Wu · Jie Xiao · Nianzu Yang · Jieyi Bi · Jian Yao · Yiting Chen · Qizhou Wang · Yangru Huang · Yongqiang Chen · Peixi Peng · Yuxin Hong · Xintao Wang · Feng Liu · Yining Ma · Qibing Ren · Xueyang Fu · Yonggang Zhang · Kaipeng Zeng · Jiahai Wang · GEN LI · Yonggang Zhang · Qitian Wu · Yifan Zhao · Chiyu Wang · Junchi Yan · Feng Wu · Yatao Bian · Xiaosong Jia · Ying Shan · Zhiguang Cao · Zheng-Jun Zha · Guangyao Chen · Tianjun Xiao · Han Yang · Jing Zhang · Jinbiao Chen · MA Kaili · Yonghong Tian · Junchi Yan · Chen Gong · Tong He · Binghui Xie · Yuan Sun · Francesco Locatello · Tongliang Liu · Yeow Meng Chee · David P Wipf · Tongliang Liu · Bo Han · Bo Han · Yanwei Fu · James Cheng · Zheng Zhang -
2022 Spotlight: AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos »
Yanze Wu · Xintao Wang · GEN LI · Ying Shan -
2022 Poster: DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes »
Jia-Wei Liu · Yan-Pei Cao · Weijia Mao · Wenqiao Zhang · David Junhao Zhang · Jussi Keppo · Ying Shan · Xiaohu Qie · Mike Zheng Shou -
2021 Poster: Dirichlet Energy Constrained Learning for Deep Graph Neural Networks »
Kaixiong Zhou · Xiao Huang · Daochen Zha · Rui Chen · Li Li · Soo-Hyun Choi · Xia Hu -
2021 Poster: Fairness via Representation Neutralization »
Mengnan Du · Subhabrata Mukherjee · Guanchu Wang · Ruixiang Tang · Ahmed Awadallah · Xia Hu -
2021 Poster: Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution »
Liangbin Xie · Xintao Wang · Chao Dong · Zhongang Qi · Ying Shan -
2020 Poster: Towards Deeper Graph Neural Networks with Differentiable Group Normalization »
Kaixiong Zhou · Xiao Huang · Yuening Li · Daochen Zha · Rui Chen · Xia Hu