Reasoning presents a significant and challenging issue for Large Languag...
Large-scale pre-trained models have been remarkably successful in resolv...
Reinforcement learning is an essential paradigm for solving sequential
d...
Personalized federated learning (PFL) jointly trains a variety of local
...
A robust summarization system should be able to capture the gist of the
...
How to train a generalizable meta-policy by continually learning a seque...
Federated weather forecasting is a promising collaborative learning fram...
Information retrieval (IR) plays a crucial role in locating relevant
res...
In this work, we propose a simple method that applies a large language m...
Distribution shift (e.g., task or domain shift) in continual learning (C...
Recently, Fourier transform has been widely introduced into deep neural
...
As a few large-scale pre-trained models become the major choices of vari...
Existing multi-style image captioning methods show promising results in
...
Text-guided image inpainting (TGII) aims to restore missing regions base...
Image-guided story ending generation (IgSEG) is to generate a story endi...
To tackle the global climate challenge, it urgently needs to develop a
c...
With rising concerns about privacy, developing recommendation systems in...
Long document retrieval aims to fetch query-relevant documents from a
la...
Graph neural networks (GNNs) have shown their superiority in modeling gr...
With the advance of natural language inference (NLI), a rising demand fo...
Federated Learning (FL) is a machine learning paradigm that allows
decen...
A ranker plays an indispensable role in the de facto 'retrieval rera...
Federated learning (FL) aims at training a global model on the server si...
Generating new events given context with correlated ones plays a crucial...
In a federated learning system, the clients, e.g. mobile devices and
org...
Event correlation reasoning infers whether a natural language paragraph
...
Sequential diagnosis prediction on the Electronic Health Record (EHR) ha...
Aspect-level sentiment classification (ALSC) aims at identifying the
sen...
Privacy protection is an ethical issue with broad concern in Artificial
...
Open banking enables individual customers to own their banking data, whi...
Healthcare representation learning on the Electronic Health Record (EHR)...
Graph convolutional networks are becoming indispensable for deep learnin...
The heterogeneity across devices usually hinders the optimization conver...
Zero-shot learning (ZSL) refers to the problem of learning to classify
i...
Federated learning is a new learning paradigm that decouples data collec...
Zero-shot learning (ZSL) aims to classify images of an unseen class only...
Deep learning with noisy labels is a challenging task. Recent prominent
...
Few-shot image classification is challenging due to the lack of ample sa...
Numerous deep reinforcement learning agents have been proposed, and each...
Many graph embedding approaches have been proposed for knowledge graph
c...
The goal of zero-shot learning (ZSL) is to train a model to classify sam...
Electronic health records (EHRs) are longitudinal records of a patient's...
We study many-class few-shot (MCFS) problem in both supervised learning ...
Few-shot classification aims to recognize unseen classes when presented ...
Recent few-shot learning works focus on training a model with prior
meta...
Modeling multivariate time series has long been a subject that has attra...
Federated learning has received great attention for its capability to tr...
We improve both the open-set generalization and efficiency of link predi...
In this work, we aim at equipping pre-trained language models with struc...
For time series classification task using 1D-CNN, the selection of kerne...