Advances in collaborative filtering

Y Koren, S Rendle, R Bell - Recommender systems handbook, 2021‏ - Springer
Collaborative filtering (CF) methods produce recommendations based on usage patterns
without the need of exogenous information about items or users. CF algorithms have shown …

Neural collaborative filtering vs. matrix factorization revisited

S Rendle, W Krichene, L Zhang… - Proceedings of the 14th …, 2020‏ - dl.acm.org
Embedding based models have been the state of the art in collaborative filtering for over a
decade. Traditionally, the dot product or higher order equivalents have been used to …

How powerful is graph convolution for recommendation?

Y Shen, Y Wu, Y Zhang, C Shan, J Zhang… - Proceedings of the 30th …, 2021‏ - dl.acm.org
Graph convolutional networks (GCNs) have recently enabled a popular class of algorithms
for collaborative filtering (CF). Nevertheless, the theoretical underpinnings of their empirical …

On the difficulty of evaluating baselines: A study on recommender systems

S Rendle, L Zhang, Y Koren - arxiv preprint arxiv:1905.01395, 2019‏ - arxiv.org
Numerical evaluations with comparisons to baselines play a central role when judging
research in recommender systems. In this paper, we show that running baselines properly is …

Parameter-free dynamic graph embedding for link prediction

J Liu, D Li, H Gu, T Lu, P Zhang… - Advances in Neural …, 2022‏ - proceedings.neurips.cc
Dynamic interaction graphs have been widely adopted to model the evolution of user-item
interactions over time. There are two crucial factors when modelling user preferences for link …

Modeling dynamic missingness of implicit feedback for recommendation

M Wang, M Gong, X Zheng… - Advances in neural …, 2018‏ - proceedings.neurips.cc
Implicit feedback is widely used in collaborative filtering methods for recommendation. It is
well known that implicit feedback contains a large number of values that are\emph {missing …

Learning with noisy labels by efficient transition matrix estimation to combat label miscorrection

SM Kye, K Choi, J Yi, B Chang - European Conference on Computer …, 2022‏ - Springer
Recent studies on learning with noisy labels have shown remarkable performance by
exploiting a small clean dataset. In particular, model agnostic meta-learning-based label …

Learning hierarchical preferences for recommendation with mixture intention neural stochastic processes

H Liu, M Zhou, M Song, D Ouyang, Y Li… - … on Knowledge and …, 2024‏ - ieeexplore.ieee.org
User preferences behind users' decision-making processes are highly diverse and may
range from lower-level concepts with more specific intentions and higher-level concepts with …

Learning self-modulating attention in continuous time space with applications to sequential recommendation

C Chen, H Geng, N Yang, J Yan… - International …, 2021‏ - proceedings.mlr.press
User interests are usually dynamic in the real world, which poses both theoretical and
practical challenges for learning accurate preferences from rich behavior data. Among …

Triple structural information modelling for accurate, explainable and interactive recommendation

J Liu, D Li, H Gu, T Lu, P Zhang, L Shang… - Proceedings of the 46th …, 2023‏ - dl.acm.org
In dynamic interaction graphs, user-item interactions usually follow heterogeneous patterns,
represented by different structural information, such as user-item co-occurrence, sequential …