Search Results for author: Longbing Cao

Found 46 papers, 9 papers with code

Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation

no code implementations EMNLP 2021 Tianfu Zhang, Heyan Huang, Chong Feng, Longbing Cao

Multi-head self-attention recently attracts enormous interest owing to its specialized functions, significant parallelizable computation, and flexible extensibility.

Machine Translation Translation

Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective

no code implementations27 Jan 2023 Hui He, Qi Zhang, Shoujin Wang, Kun Yi, Zhendong Niu, Longbing Cao

To address this significant gap, we formulate the MTS fairness modeling problem as learning informative representations attending to both advantaged and disadvantaged variables.

Fairness Multivariate Time Series Forecasting

eVAE: Evolutionary Variational Autoencoder

1 code implementation1 Jan 2023 Zhangkai Wu, Longbing Cao, Lei Qi

VAEs still suffer from uncertain tradeoff learning. We propose a novel evolutionary variational autoencoder (eVAE) building on the variational information bottleneck (VIB) theory and integrative evolutionary neural learning.

Disentanglement Image Generation +1

Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing

1 code implementation5 Nov 2022 Rui Yu, Yifeng Li, Wenpeng Lu, Longbing Cao

In natural language processing (NLP), the context of a word or sentence plays an essential role.

Edge-Varying Fourier Graph Networks for Multivariate Time Series Forecasting

no code implementations6 Oct 2022 Kun Yi, Qi Zhang, Liang Hu, Hui He, Ning An, Longbing Cao, Zhendong Niu

The key problem in multivariate time series (MTS) analysis and forecasting aims to disclose the underlying couplings between variables that drive the co-movements.

Multivariate Time Series Forecasting

Supervised Deep Hashing for High-dimensional and Heterogeneous Case-based Reasoning

no code implementations29 Jun 2022 Qi Zhang, Liang Hu, Chongyang Shi, Ke Liu, Longbing Cao

Case-based Reasoning (CBR) on high-dimensional and heterogeneous data is a trending yet challenging and computationally expensive task in the real world.

Incremental Learning Quantization +1

Supervision Adaptation Balances In-Distribution Generalization and Out-of-Distribution Detection

no code implementations19 Jun 2022 Zhilin Zhao, Longbing Cao, Kun-Yu Lin

To improve the OOD sensitivity of deep networks, several state-of-the-art methods introduce samples from other real-world datasets as OOD samples to the training process and assign manually-determined labels to these OOD samples.

Out-of-Distribution Detection Out of Distribution (OOD) Detection

Out-of-distribution Detection by Cross-class Vicinity Distribution of In-distribution Data

no code implementations19 Jun 2022 Zhilin Zhao, Longbing Cao, Kun-Yu Lin

We thus improve the discriminability of a pretrained network by finetuning it with out-of-distribution samples drawn from the cross-class vicinity distribution, where each out-of-distribution input corresponds to a complementary label.

Out-of-Distribution Detection

Label and Distribution-discriminative Dual Representation Learning for Out-of-Distribution Detection

1 code implementation19 Jun 2022 Zhilin Zhao, Longbing Cao

Specifically, networks extract the strongly label-related information from in-distribution samples to learn the label-discriminative representations but discard the weakly label-related information.

Informativeness Out-of-Distribution Detection +1

Gray Learning from Non-IID Data with Out-of-distribution Samples

no code implementations19 Jun 2022 Zhilin Zhao, Longbing Cao, Chang-Dong Wang

With this insight, we propose a novel \textit{gray learning} approach to robustly learn from non-IID data with both in- and out-of-distribution samples.

Learning Theory

Explicit and Implicit Pattern Relation Analysis for Discovering Actionable Negative Sequences

no code implementations4 Apr 2022 Wei Wang, Longbing Cao

A DPP-based NSP representation and actionable NSP discovery method EINSP introduces novel and significant contributions for NSA and sequence analysis: (1) it represents NSPs by a determinantal point process (DPP) based graph; (2) it quantifies actionable NSPs in terms of their statistical significance, diversity, and strength of explicit/implicit element/pattern relations; and (3) it models and measures both explicit and implicit element/pattern relations in the DPP-based NSP graph to represent direct and indirect couplings between NSP items, elements and patterns.

Decision Making

Coupling Online-Offline Learning for Multi-distributional Data Streams

no code implementations12 Feb 2022 Zhilin Zhao, Longbing Cao, Yuanyu Wan

CO$_2$ extracts knowledge by training an offline expert for each offline interval and update an online expert by an off-the-shelf online optimization method in the online interval.

Transfer Learning

Table2Vec: Automated Universal Representation Learning to Encode All-round Data DNA for Benchmarkable and Explainable Enterprise Data Science

no code implementations3 Dec 2021 Longbing Cao, Chengzhang Zhu

The learned universal representation of each customer is all-round, representative and benchmarkable to support both enterprise-wide and domain-specific learning goals and tasks in enterprise data science.

Decision Making Management +2

Revealing the Distributional Vulnerability of Discriminators by Implicit Generators

1 code implementation23 Aug 2021 Zhilin Zhao, Longbing Cao, Kun-Yu Lin

According to the Shannon entropy, an energy-based implicit generator is inferred from a discriminator without extra training costs.

Out of Distribution (OOD) Detection

Modeling time evolving COVID-19 uncertainties with density dependent asymptomatic infections and social reinforcement

no code implementations23 Aug 2021 Qing Liu, Longbing Cao

Different from existing COVID-19 models, SUDR characterizes the undocumented infections during unknown transmission processes.

Bayesian Inference

Personalized next-best action recommendation with multi-party interaction learning for automated decision-making

no code implementations19 Aug 2021 Longbing Cao, Chengzhang Zhu

CRN represents multiple coupled dynamic sequences of a customer's historical and current states, responses to decision-makers' actions, decision rewards to actions, and learns long-term multi-sequence interactions between parties (customer and decision-maker).

Decision Making Sequential Recommendation

DeepExpress: Heterogeneous and Coupled Sequence Modeling for Express Delivery Prediction

no code implementations18 Aug 2021 Siyuan Ren, Bin Guo, Longbing Cao, Ke Li, Jiaqi Liu, Zhiwen Yu

To address these issues, we propose DeepExpress - a deep-learning based express delivery sequence prediction model, which extends the classic seq2seq framework to learning complex coupling between sequence and features.

AI in Finance: Challenges, Techniques and Opportunities

no code implementations20 Jul 2021 Longbing Cao

The landscapes and challenges of financial businesses and data are firstly outlined, followed by a comprehensive categorization and a dense overview of the decades of AI research in finance.

Recurrent Coupled Topic Modeling over Sequential Documents

no code implementations23 Jun 2021 Jinjin Guo, Longbing Cao, Zhiguo Gong

The abundant sequential documents such as online archival, social media and news feeds are streamingly updated, where each chunk of documents is incorporated with smoothly evolving yet dependent topics.

Data Augmentation Dynamic Topic Modeling

Graph Learning based Recommender Systems: A Review

1 code implementation13 May 2021 Shoujin Wang, Liang Hu, Yan Wang, Xiangnan He, Quan Z. Sheng, Mehmet A. Orgun, Longbing Cao, Francesco Ricci, Philip S. Yu

Recent years have witnessed the fast development of the emerging topic of Graph Learning based Recommender Systems (GLRS).

Collaborative Filtering Graph Learning +1

COVID-19 Modeling: A Review

no code implementations16 Apr 2021 Longbing Cao, Qing Liu

The SARS-CoV-2 virus and COVID-19 disease have posed unprecedented and overwhelming demand, challenges and opportunities to domain, model and data driven modeling.


Homophily Outlier Detection in Non-IID Categorical Data

no code implementations21 Mar 2021 Guansong Pang, Longbing Cao, Ling Chen

Most of existing outlier detection methods assume that the outlier factors (i. e., outlierness scoring measures) of data entities (e. g., feature values and data objects) are Independent and Identically Distributed (IID).

Outlier Detection

Unsupervised Heterogeneous Coupling Learning for Categorical Representation

no code implementations21 Jul 2020 Chengzhang Zhu, Longbing Cao, Jianping Yin

This work introduces a shallow but powerful UNsupervised heTerogeneous couplIng lEarning (UNTIE) approach for representing coupled categorical data by untying the interactions between couplings and revealing heterogeneous distributions embedded in each type of couplings.


Data science and AI in FinTech: An overview

no code implementations10 Jul 2020 Longbing Cao, Qiang Yang, Philip S. Yu

Financial technology (FinTech) has been playing an increasingly critical role in driving modern economies, society, technology, and many other areas.

BIG-bench Machine Learning Federated Learning +1

Deep Learning for Anomaly Detection: A Review

no code implementations6 Jul 2020 Guansong Pang, Chunhua Shen, Longbing Cao, Anton Van Den Hengel

This paper surveys the research of deep anomaly detection with a comprehensive taxonomy, covering advancements in three high-level categories and 11 fine-grained categories of the methods.

Anomaly Detection Outlier Detection

Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting

no code implementations1 Jul 2020 Longbing Cao

While recommendation plays an increasingly critical role in our living, study, work, and entertainment, the recommendations we receive are often for irrelevant, duplicate, or uninteresting products and services.

Recommendation Systems

Data Science: A Comprehensive Overview

no code implementations1 Jul 2020 Longbing Cao

This paper provides a comprehensive survey and tutorial of the fundamental aspects of data science: the evolution from data analysis to data science, the data science concepts, a big picture of the era of data science, the major challenges and directions in data innovation, the nature of data analytics, new industrialization and service opportunities in the data economy, the profession and competency of data education, and the future of data science.

Computers and Society

Coupling Learning of Complex Interactions

no code implementations1 Jul 2020 Longbing Cao

Complex applications such as big data analytics involve different forms of coupling relationships that reflect interactions between factors related to technical, business (domain-specific) and environmental (including socio-cultural and economic) aspects.

Association Recommendation Systems

Jointly Modeling Intra- and Inter-transaction Dependencies with Hierarchical Attentive Transaction Embeddings for Next-item Recommendation

no code implementations30 May 2020 Shoujin Wang, Longbing Cao, Liang Hu, Shlomo Berkovsky, Xiaoshui Huang, Lin Xiao, Wenpeng Lu

Most existing TBRSs recommend next item by only modeling the intra-transaction dependency within the current transaction while ignoring inter-transaction dependency with recent transactions that may also affect the next item.

Recommendation Systems

Sequential Recommender Systems: Challenges, Progress and Prospects

no code implementations28 Dec 2019 Shoujin Wang, Liang Hu, Yan Wang, Longbing Cao, Quan Z. Sheng, Mehmet Orgun

The emerging topic of sequential recommender systems has attracted increasing attention in recent years. Different from the conventional recommender systems including collaborative filtering and content-based filtering, SRSs try to understand and model the sequential user behaviors, the interactions between users and items, and the evolution of users preferences and item popularity over time.

Collaborative Filtering Recommendation Systems

FiDi-RL: Incorporating Deep Reinforcement Learning with Finite-Difference Policy Search for Efficient Learning of Continuous Control

no code implementations1 Jul 2019 Longxiang Shi, Shijian Li, Longbing Cao, Long Yang, Gang Zheng, Gang Pan

Alternatively, derivative-based methods treat the optimization process as a blackbox and show robustness and stability in learning continuous control tasks, but not data efficient in learning.

Continuous Control reinforcement-learning +1

Multi-view Information-theoretic Co-clustering for Co-occurrence Data

1 code implementation25 May 2019 Peng Xu, Zhaohong Deng, Kup-Sze Choi, Longbing Cao, Shitong Wang

More specifically, it exploits the agreement and disagreement among views by sharing a common clustering results along the sample dimension and keeping the clustering results of each view specific along the feature dimension.

TBQ($σ$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning

no code implementations17 May 2019 Longxiang Shi, Shijian Li, Longbing Cao, Long Yang, Gang Pan

However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems.

reinforcement-learning Reinforcement Learning (RL)

A Survey on Session-based Recommender Systems

1 code implementation13 Feb 2019 Shoujin Wang, Longbing Cao, Yan Wang, Quan Z. Sheng, Mehmet Orgun, Defu Lian

In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs.

Collaborative Filtering Decision Making +1

Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence

no code implementations NeurIPS 2018 Trong Dinh Thac Do, Longbing Cao

A conjugate Gamma-Poisson model for Dynamic Matrix Factorization incorporated with metadata influence (mGDMF for short) is proposed to effectively and efficiently model massive, sparse and dynamic data in recommendations.

Variational Inference

Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection

3 code implementations13 Jun 2018 Guansong Pang, Longbing Cao, Ling Chen, Huan Liu

However, existing unsupervised representation learning methods mainly focus on preserving the data regularity information and learning the representations independently of subsequent outlier detection methods, which can result in suboptimal and unstable performance of detecting irregularities (i. e., outliers).

Anomaly Detection Disease Prediction +3

CSAL: Self-adaptive Labeling based Clustering Integrating Supervised Learning on Unlabeled Data

no code implementations18 Feb 2015 Fangfang Li, Guandong Xu, Longbing Cao

In this paper, we propose an innovative and effective clustering framework based on self-adaptive labeling (CSAL) which integrates clustering and classification on unlabeled data.

Classification General Classification

Coupled Item-based Matrix Factorization

no code implementations8 Apr 2014 Fangfang Li, Guandong Xu, Longbing Cao

The essence of the challenges cold start and sparsity in Recommender Systems (RS) is that the extant techniques, such as Collaborative Filtering (CF) and Matrix Factorization (MF), mainly rely on the user-item rating matrix, which sometimes is not informative enough for predicting recommendations.

Collaborative Filtering Recommendation Systems

Learning Hidden Structures with Relational Models by Adequately Involving Rich Information in A Network

no code implementations6 Oct 2013 Xuhui Fan, Richard Yi Da Xu, Longbing Cao, Yin Song

In this work, we propose an informative relational model (InfRM) framework to adequately involve rich information and its granularity in a network, including metadata information about each entity and various forms of link data.

Non-parametric Power-law Data Clustering

no code implementations13 Jun 2013 Xuhui Fan, Yiling Zeng, Longbing Cao

However, several problems remains unsolved in this pioneering work, including the power-law data applicability, mechanism to merge centers to avoid the over-fitting problem, clustering order problem, e. t. c.. To address these issues, the Pitman-Yor Process based k-means (namely \emph{pyp-means}) is proposed in this paper.

Variational Inference

Dynamic Infinite Mixed-Membership Stochastic Blockmodel

no code implementations13 Jun 2013 Xuhui Fan, Longbing Cao, Richard Yi Da Xu

Directional and pairwise measurements are often used to model inter-relationships in a social network setting.

A Convergence Theorem for the Graph Shift-type Algorithms

no code implementations13 Jun 2013 Xuhui Fan, Longbing Cao

Graph Shift (GS) algorithms are recently focused as a promising approach for discovering dense subgraphs in noisy data.

Copula Mixed-Membership Stochastic Blockmodel for Intra-Subgroup Correlations

no code implementations12 Jun 2013 Xuhui Fan, Longbing Cao, Richard Yi Da Xu

To this end, we introduce a \emph{Copula Mixed-Membership Stochastic Blockmodel (cMMSB)} where an individual Copula function is employed to jointly model the membership pairs of those nodes within the subgroup of interest.

Link Prediction

Characterizing A Database of Sequential Behaviors with Latent Dirichlet Hidden Markov Models

no code implementations24 May 2013 Yin Song, Longbing Cao, Xuhui Fan, Wei Cao, Jian Zhang

These sequence-level latent parameters for each sequence are modeled as latent Dirichlet random variables and parameterized by a set of deterministic database-level hyper-parameters.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.