As a specific case of graph transfer learning, unsupervised domain adapt...
Accurate traffic forecasting at intersections governed by intelligent tr...
Machine learning algorithms have become ubiquitous in a number of
applic...
The rapid development of online recruitment services has encouraged the
...
In today's competitive and fast-evolving business environment, it is a
c...
Document-level event extraction is a long-standing challenging informati...
Feature transformation aims to reconstruct an effective representation s...
Graph Neural Networks (GNNs) have been broadly applied in many urban
app...
Accurate Urban SpatioTemporal Prediction (USTP) is of great importance t...
Contrastive learning (CL) has become the de-facto learning paradigm in
s...
Class imbalance is the phenomenon that some classes have much fewer inst...
Finding multiple temporal relationships among locations can benefit a bu...
Large Language Models (LLMs) have emerged as powerful tools in the field...
Generating and editing a 3D scene guided by natural language poses a
cha...
End-to-end sign language translation (SLT) aims to convert sign language...
People usually have different intents for choosing items, while their
pr...
Recent years have witnessed the rapid development of heterogeneous graph...
The outbreak of the COVID-19 pandemic has had an unprecedented impact on...
Recent research endeavors have shown that combining neural radiance fiel...
Although remarkable progress on the neural table-to-text methods has bee...
Urban villages (UVs) refer to the underdeveloped informal settlement fal...
The peer merit review of research proposals has been the major mechanism...
Feature transformation aims to extract a good representation (feature) s...
As a successful approach to self-supervised learning, contrastive learni...
While self-supervised learning techniques are often used to mining impli...
Conversational recommender systems (CRS) aim to capture user's current
i...
Traffic demand forecasting by deep neural networks has attracted widespr...
Contrastive learning (CL)-based self-supervised learning models learn vi...
Recent studies have shown great promise in applying graph neural network...
In e-commerce, online retailers are usually suffering from professional
...
Feature selection and instance selection are two important techniques of...
Mobile user profiling refers to the efforts of extracting users'
charact...
What matters for contrastive learning? We argue that contrastive learnin...
Unsupervised domain adaptation (UDA) requires source domain samples with...
Graph neural networks generalize conventional neural networks to
graph-s...
In this paper, we focus on the problem of modeling dynamic geo-human
int...
Human mobility data accumulated from Point-of-Interest (POI) check-ins
p...
Graph walking based on reinforcement learning (RL) has shown great succe...
Earnings call (EC), as a periodic teleconference of a publicly-traded
co...
Motivated by the success of pre-trained language models such as BERT in ...
Nowadays, Knowledge graphs (KGs) have been playing a pivotal role in
AI-...
As one of the most popular generative models, Variational Autoencoder (V...
The task of image captioning aims to generate captions directly from ima...
Trip recommender system, which targets at recommending a trip consisting...
Recently many efforts have been devoted to applying graph neural network...
Multi-view representation learning captures comprehensive information fr...
Drug discovery often relies on the successful prediction of protein-liga...
Real estate appraisal refers to the process of developing an unbiased op...
Anomalies represent rare observations (e.g., data records or events) tha...
Representation learning on heterogeneous graphs aims to obtain meaningfu...