activity
20182022
most citedDecoupling the Depth and Scope of Graph Neural Networks

54 citations · 76 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG202254 cited

Decoupling the Depth and Scope of Graph Neural Networks

Hanqing Zeng, Muhan Zhang, Yinglong Xia +6

State-of-the-art Graph Neural Networks (GNNs) have limited scalability with respect to the graph and model sizes. On large graphs, increasing the model depth often means exponentia…

cs.IR20206 cited

Time-based Sequence Model for Personalization and Recommendation Systems

Tigran Ishkhanov, Maxim Naumov, Xianjie Chen +7

In this paper we develop a novel recommendation model that explicitly incorporates time information. The model relies on an embedding layer and TSL attention-like mechanism with in…

cs.LG201916 cited

Post-Training 4-bit Quantization on Embedding Tables

Hui Guan, Andrey Malevich, Jiyan Yang +2

Continuous representations have been widely adopted in recommender systems where a large number of entities are represented using embedding vectors. As the cardinality of the entit…

cs.DC2019

The Architectural Implications of Facebook's DNN-based Personalized Recommendation

Udit Gupta, Carole-Jean Wu, Xiaodong Wang +12

The widespread application of deep learning has changed the landscape of computation in the data center. In particular, personalized recommendation for content ranking is now large…

cs.LG2018

Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications

Jongsoo Park, Maxim Naumov, Protonu Basu +25

The application of deep learning techniques resulted in remarkable improvement of machine learning models. In this paper provides detailed characterizations of deep learning models…