Search Results for author:
Found 67 papers, 19 papers with code
Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation
Multi-head self-attention recently attracts enormous interest owing to its specialized functions, significant parallelizable computation, and flexible extensibility.
Marked Temporal Bayesian Flow Point Processes
Additionally, by adding joint noise to the marked temporal data space, BMTPP effectively captures and explicitly reveals the interdependence between timestamps and event types.
Federated Neural Nonparametric Point Processes
Temporal point processes (TPPs) are effective for modeling event occurrences over time, but they struggle with sparse and uncertain events in federated systems, where privacy is a major concern.
Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach
In this paper, we study the adversarial vulnerability of recent VLP transformers and design a novel Joint Multimodal Transformer Feature Attack (JMTFA) that concurrently introduces adversarial perturbations in both visual and textual modalities under white-box settings.
Can LLMs Serve As Time Series Anomaly Detectors?
An emerging topic in large language models (LLMs) is their application to time series forecasting, characterizing mainstream and patternable characteristics of time series.
Graph Memory Learning: Imitating Lifelong Remembering and Forgetting of Brain Networks
BGML incorporates a multi-granular hierarchical progressive learning mechanism rooted in feature graph grain learning to mitigate potential conflict between memorization and forgetting in graph memory learning.
Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift
The non-stationary nature of real-world Multivariate Time Series (MTS) data presents forecasting models with a formidable challenge of the time-variant distribution of time series, referred to as distribution shift.
ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks
Specifically, ParamReL proposes a \emph{self-}encoder to learn latent semantics directly from parameters, rather than from observations.
FedSI: Federated Subnetwork Inference for Efficient Uncertainty Quantification
While deep neural networks (DNNs) based personalized federated learning (PFL) is demanding for addressing data heterogeneity and shows promising performance, existing methods for federated learning (FL) suffer from efficient systematic uncertainty quantification.
Causal Learning for Trustworthy Recommender Systems: A Survey
However, emerging vulnerabilities in RS have catalyzed a paradigm shift towards Trustworthy RS (TRS).
DE$^3$-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks
DE$^3$-BERT implements a hybrid exiting strategy that supplements classic entropy-based local information with distance-based global information to enhance the estimation of prediction correctness for more reliable early exiting decisions.
Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection
Due to their unsupervised training and uncertainty estimation, deep Variational Autoencoders (VAEs) have become powerful tools for reconstruction-based Time Series Anomaly Detection (TSAD).
Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector
Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media.
Distilling the Unknown to Unveil Certainty
This paper introduces OOD knowledge distillation, a pioneering learning framework applicable whether or not training ID data is available, given a standard network.
FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective
Multivariate time series (MTS) forecasting has shown great importance in numerous industries.
Graph Neural Network
Multivariate Time Series Forecasting
+1
Frequency-domain MLPs are More Effective Learners in Time Series Forecasting
FreTS mainly involves two stages, (i) Domain Conversion, that transforms time-domain signals into complex numbers of frequency domain; (ii) Frequency Learning, that performs our redesigned MLPs for the learning of real and imaginary part of frequency components.
Bayesian Personalized Federated Learning with Shared and Personalized Uncertainty Representations
BPFL aims to quantify the uncertainty and heterogeneity within and across clients towards uncertainty representations by addressing the statistical heterogeneity of client data.
C$^2$VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior
Then, a self-supervised contrastive classifier differentiates the disentangled representations from the coupled representations, where a contrastive loss regularizes this contrastive classification together with the TC loss for eliminating entangled factors and strengthening disentangled representations.
Copula Variational LSTM for High-dimensional Cross-market Multivariate Dependence Modeling
Our variational neural network WPVC-VLSTM models variational sequential dependence degrees and structures across multivariate time series by variational long short-term memory networks and regular vine copula.
Bayesian Federated Learning: A Survey
This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives.
A Survey on Deep Learning based Time Series Analysis with Frequency Transformation
Despite the growing attention and the proliferation of research in this emerging field, there is currently a lack of a systematic review and in-depth analysis of deep learning-based time series models with FT.
Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective
To bridge such significant gap, we formulate the fairness modeling problem as learning informative representations attending to both advantaged and disadvantaged variables.
eVAE: Evolutionary Variational Autoencoder
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.
Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing
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
The key problem in multivariate time series (MTS) analysis and forecasting aims to disclose the underlying couplings between variables that drive the co-movements.
Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting
Most existing MTS forecasting models greatly suffer from distribution drift and degrade the forecasting performance over time.
Supervised Deep Hashing for High-dimensional and Heterogeneous Case-based Reasoning
Case-based Reasoning (CBR) on high-dimensional and heterogeneous data is a trending yet challenging and computationally expensive task in the real world.
Out-of-distribution Detection by Cross-class Vicinity Distribution of In-distribution Data
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.
Dual Representation Learning for Out-of-Distribution Detection
To distinguish in- and out-of-distribution samples, Dual Representation Learning (DRL) makes out-of-distribution samples harder to have high-confidence predictions by exploring both strongly and weakly label-related information from in-distribution samples.
Supervision Adaptation Balancing In-distribution Generalization and Out-of-distribution Detection
To tackle this issue, several state-of-the-art methods include adding extra OOD samples to training and assign them with manually-defined labels.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Gray Learning from Non-IID Data with Out-of-distribution Samples
We observe that both in- and out-of-distribution samples can almost invariably be ruled out from belonging to certain classes, aside from those corresponding to unreliable ground-truth labels.
Explicit and Implicit Pattern Relation Analysis for Discovering Actionable Negative Sequences
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.
Mixture of Online and Offline Experts for Non-stationary Time Series
MOOE learns static offline experts from offline intervals and maintains a dynamic online expert for the current online interval.
Table2Vec: Automated Universal Representation Learning to Encode All-round Data DNA for Benchmarkable and Explainable Enterprise Data Science
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.
Modeling time evolving COVID-19 uncertainties with density dependent asymptomatic infections and social reinforcement
Different from existing COVID-19 models, SUDR characterizes the undocumented infections during unknown transmission processes.
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators
According to the Shannon entropy, an energy-based implicit generator is inferred from a discriminator without extra training costs.
Personalized next-best action recommendation with multi-party interaction learning for automated decision-making
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).
DeepExpress: Heterogeneous and Coupled Sequence Modeling for Express Delivery Prediction
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
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
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.
Graph Learning based Recommender Systems: A Review
Recent years have witnessed the fast development of the emerging topic of Graph Learning based Recommender Systems (GLRS).
COVID-19 Modeling: A Review
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
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).
Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset.
Unsupervised Heterogeneous Coupling Learning for Categorical Representation
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
Financial technology (FinTech) has been playing an increasingly critical role in driving modern economies, society, technology, and many other areas.
Deep Learning for Anomaly Detection: A Review
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.
Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting
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.
Data Science: A Comprehensive Overview
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
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.
Jointly Modeling Intra- and Inter-transaction Dependencies with Hierarchical Attentive Transaction Embeddings for Next-item Recommendation
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.
Graph Learning Approaches to Recommender Systems: A Review
Recent years have witnessed the fast development of the emerging topic of Graph Learning based Recommender Systems (GLRS).
Sequential Recommender Systems: Challenges, Progress and Prospects
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.
FiDi-RL: Incorporating Deep Reinforcement Learning with Finite-Difference Policy Search for Efficient Learning of Continuous Control
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.
Multi-view Information-theoretic Co-clustering for Co-occurrence Data
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
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.
A Survey on Session-based Recommender Systems
In recent years, session-based recommender systems (SBRSs) have emerged as a new paradigm of RSs.
Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence
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.
Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection
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).
CSAL: Self-adaptive Labeling based Clustering Integrating Supervised Learning on Unlabeled Data
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.
Coupled Item-based Matrix Factorization
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.
Learning Hidden Structures with Relational Models by Adequately Involving Rich Information in A Network
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.
Dynamic Infinite Mixed-Membership Stochastic Blockmodel
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
Graph Shift (GS) algorithms are recently focused as a promising approach for discovering dense subgraphs in noisy data.
Non-parametric Power-law Data Clustering
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.
Copula Mixed-Membership Stochastic Blockmodel for Intra-Subgroup Correlations
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.
Characterizing A Database of Sequential Behaviors with Latent Dirichlet Hidden Markov Models
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.
