Learning Transferrable Parameters for Long-tailed Sequential User Behavior Modeling

@article{Yin2020LearningTP,
  title={Learning Transferrable Parameters for Long-tailed Sequential User Behavior Modeling},
  author={Jianwen Yin and Chenghao Liu and Weiqing Wang and Jianling Sun and Steven C. H. Hoi},
  journal={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
  year={2020}
}
  • Jianwen YinChenghao Liu S. Hoi
  • Published 6 July 2020
  • Computer Science
  • Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
Sequential user behavior modeling plays a crucial role in online user-oriented services, such as product purchasing, news feed consumption, and online advertising. The performance of sequential modeling heavily depends on the scale and quality of historical behaviors. However, the number of user behaviors inherently follows a long-tailed distribution, which has been seldom explored. In this work, we argue that focusing on tail users could bring more benefits and address the long tails issue by… 
View on ACM
[PDF] Semantic Reader
14 Citations
Highly Influential Citations
2
Background Citations
11
Methods Citations
2

Figures and Tables from this paper

14 Citations

Personalizing Intervened Network for Long-tailed Sequential User Behavior Modeling

A novel Gradient Aggregation technique that learns common knowledge shared by all users into a backbone model, fol-lowed by separate plugin prediction networks for the head users and the tail users personalization is proposed.

Harmless Transfer Learning for Item Embeddings

This work proposes a harmless transfer learning framework that limits the impact of the potential biases in both the definition and optimization of the transfer loss, and uses a lexicographic optimization framework to efficiently incorporate the information of thetransfer loss without hurting the minimization of the main prediction loss function.

Sequential Recommendation for Cold-start Users with Meta Transitional Learning

This work aims to improve sequential recommendation for cold-start users with a novel framework named MetaTL, which learns to model the transition patterns of users through meta-learning, which adopts meta transitional learning to enable fast learning forCold Start users with only limited interactions, leading to accurate inference of sequential interactions.

A Survey on Neural Recommendation: From Collaborative Filtering to Content and Context Enriched Recommendation

A systematic review on neural recommender models is conducted, aiming to summarize the field from the perspective of recommendation modeling, and discusses some promising directions in this field, including benchmarking recommender systems, graph reasoning based recommendation models, and explainable and fair recommendations for social good.

Mitigating Popularity Bias in Recommendation with Unbalanced Interactions: A Gradient Perspective

A gradient perspective is presented to understand two negative impacts of popularity bias in recommendation model optimization: the gradient direction of popular item embeddings is closer to that of positive interactions, and the magnitude of positive gradient for popular items are much greater than that of unpopular items.

Learning to Augment for Casual User Recommendation

A model-agnostic framework L2Aug is proposed to improve recommendations for casual users through data augmentation, without sacrificing core user experience, and outperforms other treatment methods and achieves the best sequential recommendation performance for both casual and core users.

Intent Contrastive Learning for Sequential Recommendation

Intent Contrastive Learning (ICL) is proposed, a general learning paradigm that leverages a latent variable to represent users’ intents and learn the distribution function of the latent variable via clustering in SR models via contrastive SSL.

A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation

A systematic review on neural recommender models from the perspective of recommendation modeling with the accuracy goal is conducted, aiming to summarize this field to facilitate researchers and practitioners working on recommender systems.

Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering

This paper proposes a novel OCCF framework, named as ConCF, that exploits the complementarity from heterogeneous objectives throughout the training process, generating a more generalizable model.

A Survey on Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation

A systematic review on neural recommender models from the perspective of recommendation modeling with the accuracy goal is conducted, aiming to summarize this field to facilitate researchers and practitioners working on recommender systems.

References

SHOWING 1-10 OF 39 REFERENCES

Deep Interest Network for Click-Through Rate Prediction

A novel model: Deep Interest Network (DIN) is proposed which tackles this challenge by designing a local activation unit to adaptively learn the representation of user interests from historical behaviors with respect to a certain ad.

Neural Attentive Session-based Recommendation

A novel neural networks framework, i.e., Neural Attentive Recommendation Machine (NARM), is proposed to tackle session-based recommendation, which outperforms state-of-the-art baselines on both datasets and achieves a significant improvement on long sessions.

Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation

Fossil is proposed, a similarity-based method that outperforms alternative algorithms, especially on sparse datasets, and qualitatively that it captures personalized dynamics and is able to make meaningful recommendations.

Self-Attentive Sequential Recommendation

Extensive empirical studies show that the proposed self-attention based sequential model (SASRec) outperforms various state-of-the-art sequential models (including MC/CNN/RNN-based approaches) on both sparse and dense datasets.

Fast Matrix Factorization for Online Recommendation with Implicit Feedback

A new learning algorithm based on the element-wise Alternating Least Squares (eALS) technique is designed, for efficiently optimizing a Matrix Factorization (MF) model with variably-weighted missing data and exploiting this efficiency to then seamlessly devise an incremental update strategy that instantly refreshes a MF model given new feedback.

Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding

A Convolutional Sequence Embedding Recommendation Model »Caser» is proposed, which is to embed a sequence of recent items into an image in the time and latent spaces and learn sequential patterns as local features of the image using convolutional filters.

A Simple but Hard-to-Beat Baseline for Session-based Recommendations

A simple, but very effective generative model that is capable of learning high-level representation from both short- and long-range dependencies is proposed that attains state-of-the-art accuracy with less training time in the session-based recommendation task.

Multi-Order Attentive Ranking Model for Sequential Recommendation

A Multi-order Attentive Ranking Model (MARank) is proposed to unify both individual- and union-level item interaction into preference inference model from multiple views and significantly outperforms the state-of-the-art baselines on different evaluation metrics.

Product-Based Neural Networks for User Response Prediction

  • Yanru QuHan Cai Jun Wang
  • Computer Science
    2016 IEEE 16th International Conference on Data Mining (ICDM)
  • 2016
A Product-based Neural Networks (PNN) with an embedding layer to learn a distributed representation of the categorical data, a product layer to capture interactive patterns between interfield categories, and further fully connected layers to explore high-order feature interactions.

Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference

This work proposes a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples, and introduces a new algorithm, Meta-Experience Replay, that directly exploits this view by combining experience replay with optimization based meta-learning.