49 citations · 228 across the 27 of their papers we have counts for
14 papers · 1 filter
Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs
Ling Team, Binwei Zeng, Chao Huang +71
In this technical report, we tackle the challenges of training large-scale Mixture of Experts (MoE) models, focusing on overcoming cost inefficiency and resource limitations preval…
Personalized Binomial DAGs Learning with Network Structured Covariates
Boxin Zhao, Weishi Wang, Dingyuan Zhu +5
The causal dependence in data is often characterized by Directed Acyclic Graphical (DAG) models, widely used in many areas. Causal discovery aims to recover the DAG structure using…
Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective
Jihong Wang, Minnan Luo, Jundong Li +3
Recent studies have revealed that GNNs are vulnerable to adversarial attacks. Most existing robust graph learning methods measure model robustness based on label information, rende…
Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback
Boxin Zhao, Lingxiao Wang, Ziqi Liu +4
Due to the high cost of communication, federated learning (FL) systems need to sample a subset of clients that are involved in each round of training. As a result, client sampling…
MixSeq: Connecting Macroscopic Time Series Forecasting with Microscopic Time Series Data
Zhibo Zhu, Ziqi Liu, Ge Jin +4
Time series forecasting is widely used in business intelligence, e.g., forecast stock market price, sales, and help the analysis of data trend. Most time series of interest are mac…
Bandit Samplers for Training Graph Neural Networks
Ziqi Liu, Zhengwei Wu, Zhiqiang Zhang +4
Several sampling algorithms with variance reduction have been proposed for accelerating the training of Graph Convolution Networks (GCNs). However, due to the intractable computati…
Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification
Chaochao Chen, Jun Zhou, Longfei Zheng +7
Recently, Graph Neural Network (GNN) has achieved remarkable progresses in various real-world tasks on graph data, consisting of node features and the adjacent information between…
Privacy Preserving Point-of-interest Recommendation Using Decentralized Matrix Factorization
Chaochao Chen, Ziqi Liu, Peilin Zhao +2
Points of interest (POI) recommendation has been drawn much attention recently due to the increasing popularity of location-based networks, e.g., Foursquare and Yelp. Among the exi…
Heterogeneous Graph Neural Networks for Malicious Account Detection
Ziqi Liu, Chaochao Chen, Xinxing Yang +3
We present, GEM, the first heterogeneous graph neural network approach for detecting malicious accounts at Alipay, one of the world's leading mobile cashless payment platform. Our…
How Much Can A Retailer Sell? Sales Forecasting on Tmall
Chaochao Chen, Ziqi Liu, Jun Zhou +4
Time-series forecasting is an important task in both academic and industry, which can be applied to solve many real forecasting problems like stock, water-supply, and sales predict…
A Time Attention based Fraud Transaction Detection Framework
Longfei Li, Ziqi Liu, Chaochao Chen +3
With online payment platforms being ubiquitous and important, fraud transaction detection has become the key for such platforms, to ensure user account safety and platform security…
Distributed Collaborative Hashing and Its Applications in Ant Financial
Chaochao Chen, Ziqi Liu, Peilin Zhao +3
Collaborative filtering, especially latent factor model, has been popularly used in personalized recommendation. Latent factor model aims to learn user and item latent factors from…
Distributed Deep Forest and its Application to Automatic Detection of Cash-out Fraud
Ya-Lin Zhang, Jun Zhou, Wenhao Zheng +10
Internet companies are facing the need for handling large-scale machine learning applications on a daily basis and distributed implementation of machine learning algorithms which c…
GeniePath: Graph Neural Networks with Adaptive Receptive Paths
Ziqi Liu, Chaochao Chen, Longfei Li +4
We present, GeniePath, a scalable approach for learning adaptive receptive fields of neural networks defined on permutation invariant graph data. In GeniePath, we propose an adapti…