FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data

High-order interactive features capture the correlation between different columns and thus are promising to enhance various learning tasks on ubiquitous tabular data. To automate the generation of interactive features, existing works either explicitly traverse the feature space or implicitly express the interactions via intermediate activations of some designed models. These two kinds of methods show that there is essentially a trade-off between feature interpretability and search efficiency. To possess both of their merits, we propose a novel method named Feature Interaction Via Edge Search (FIVES), which formulates the task of interactive feature generation as searching for edges on the defined feature graph. Specifically, we first present our theoretical evidence that motivates us to search for useful interactive features with increasing order. Then we instantiate this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with the defined feature graph. In this way, the proposed FIVES method simplifies the time-consuming traversal as a typical training course of GNN and enables explicit feature generation according to the learned adjacency tensor. Experimental results on both benchmark and real-world datasets show the advantages of FIVES over several state-of-the-art methods. Moreover, the interactive features identified by FIVES are deployed on the recommender system of Taobao, a worldwide leading e-commerce platform. Results of an online A/B testing further verify the effectiveness of the proposed method FIVES, and we further provide FIVES as AI utilities for the customers of Alibaba Cloud.

[1]  Hao Zhou,et al.  Network On Network for Tabular Data Classification in Real-world Applications , 2020, SIGIR.

[2]  Bin Liu,et al.  AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction , 2020, KDD.

[3]  Hao Zhou,et al.  AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications , 2019, KDD.

[4]  Rui Zhang,et al.  Detecting Beneficial Feature Interactions for Recommender Systems , 2020, AAAI.

[5]  Yiming Yang,et al.  DARTS: Differentiable Architecture Search , 2018, ICLR.

[6]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Kalyan Veeramachaneni,et al.  Deep feature synthesis: Towards automating data science endeavors , 2015, 2015 IEEE International Conference on Data Science and Advanced Analytics (DSAA).

[8]  Liang Wang,et al.  Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction , 2019, CIKM.

[9]  Isabelle Guyon,et al.  Taking Human out of Learning Applications: A Survey on Automated Machine Learning , 2018, 1810.13306.

[10]  Udayan Khurana Transformation-based Feature Engineering in Supervised Learning: Strategies toward Automation , 2018 .

[11]  Dong Lin,et al.  DCN-M: Improved Deep & Cross Network for Feature Cross Learning in Web-scale Learning to Rank Systems , 2020, ArXiv.

[12]  Vikram Pudi,et al.  AutoLearn — Automated Feature Generation and Selection , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[13]  Yuandong Tian,et al.  Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction , 2020, KDD.

[14]  Rómer Rosales,et al.  Post-click conversion modeling and analysis for non-guaranteed delivery display advertising , 2012, WSDM '12.

[15]  Andreas Krause,et al.  Advances in Neural Information Processing Systems (NIPS) , 2014 .

[16]  Wei Pan,et al.  BayesNAS: A Bayesian Approach for Neural Architecture Search , 2019, ICML.

[17]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

[18]  Yunming Ye,et al.  DeepFM: A Factorization-Machine based Neural Network for CTR Prediction , 2017, IJCAI.

[19]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[20]  Jian Tang,et al.  AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks , 2018, CIKM.

[21]  Xue Feng,et al.  Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection , 2020, ICLR.

[22]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[23]  Lihi Zelnik-Manor,et al.  XNAS: Neural Architecture Search with Expert Advice , 2019, NeurIPS.

[24]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[25]  Qiang Liu,et al.  DNN2LR: Interpretation-inspired Feature Crossing for Real-world Tabular Data , 2020, ArXiv.

[26]  Dawn Xiaodong Song,et al.  ExploreKit: Automatic Feature Generation and Selection , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[27]  Chen Lei,et al.  Automated Machine Learning , 2021, Cognitive Intelligence and Robotics.

[28]  Xing Xie,et al.  xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems , 2018, KDD.

[29]  Lihi Zelnik-Manor,et al.  ASAP: Architecture Search, Anneal and Prune , 2019, AISTATS.

[30]  Jürgen Schmidhuber,et al.  Learning Precise Timing with LSTM Recurrent Networks , 2003, J. Mach. Learn. Res..

[31]  Meng Li,et al.  SAFE: Scalable Automatic Feature Engineering Framework for Industrial Tasks , 2020, 2020 IEEE 36th International Conference on Data Engineering (ICDE).

[32]  Heng-Tze Cheng,et al.  Wide & Deep Learning for Recommender Systems , 2016, DLRS@RecSys.

[33]  Dong Yu,et al.  Deep Crossing: Web-Scale Modeling without Manually Crafted Combinatorial Features , 2016, KDD.

[34]  Song Han,et al.  ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware , 2018, ICLR.

[35]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[36]  Gang Fu,et al.  Deep & Cross Network for Ad Click Predictions , 2017, ADKDD@KDD.

[37]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[38]  Chih-Jen Lin,et al.  Field-aware Factorization Machines for CTR Prediction , 2016, RecSys.

[39]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.