Latent factor models are the dominant backbones of contemporary recommen...
The 5G networks have extensively promoted the growth of mobile users and...
Music representation learning is notoriously difficult for its complex
h...
Many text mining models are constructed by fine-tuning a large deep
pre-...
Learning unbiased node representations for imbalanced samples in the gra...
The multi-modal entity alignment (MMEA) aims to find all equivalent enti...
Graph Neural Networks (GNNs) are de facto solutions to structural data
l...
The Pretrained Foundation Models (PFMs) are regarded as the foundation f...
Contrastive Learning (CL) has been proved to be a powerful self-supervis...
Most Graph Neural Networks follow the message-passing paradigm, assuming...
Event detection in power systems aims to identify triggers and event typ...
Generally, residual connections are indispensable network components in
...
Topology-imbalance is a graph-specific imbalance problem caused by the u...
The sparse Mixture-of-Experts (MoE) model is powerful for large-scale
pr...
As more and more pre-trained language models adopt on-cloud deployment, ...
Generative adversarial network (GAN) is widely used for generalized and
...
Traffic flow prediction is an integral part of an intelligent transporta...
Local community search is an important research topic to support complex...
The goal of Knowledge Tracing (KT) is to estimate how well students have...
Knowledge graph completion (KGC) can predict missing links and is crucia...
Graph Neural Networks (GNNs) have shown promising results on a broad spe...
Graph Neural Networks (GNNs) have been widely studied in various graph d...
The outbreak of the novel Coronavirus Disease 2019 (COVID-19) has lasted...
Effective representation learning is critical for short text clustering ...
Event extraction (EE), which acquires structural event knowledge from te...
Schema-based event extraction is a critical technique to apprehend the
e...
Event extraction is a fundamental task for natural language processing.
...
Pre-trained language models achieve outstanding performance in NLP tasks...
Automatic microblog hashtag generation can help us better and faster
und...
By producing summaries for long-running events, timeline summarization (...
Neural abstractive summarization methods often require large quantities ...
Graph embedding is essential for graph mining tasks. With the prevalence...
In this paper, we propose a novel decentralized scalable learning framew...
Graph representation learning has achieved great success in many areas,
...
Graph neural networks (GNNs) have been widely used in deep learning on
g...
The current state-of-the-art model HiAGM for hierarchical text classific...
Events are happening in real-world and real-time, which can be planned a...
Since many real world networks are evolving over time, such as social
ne...
Social events provide valuable insights into group social behaviors and
...
Graph representation learning has attracted increasing research attentio...
Current annotation for plant disease images depends on manual sorting an...
Many real-world applications require the prediction of long sequence
tim...
Review rating prediction of text reviews is a rapidly growing technology...
With the advent of location-based social networks, users can tag their d...
Name disambiguation aims to identify unique authors with the same name.
...
We present Luce, the first life-long predictive model for automated prop...
Node representation learning for directed graphs is critically important...
Text classification is the most fundamental and essential task in natura...
Effective mining of social media, which consists of a large number of us...
Given a bipartite graph, the maximum balanced biclique (MBB)
problem, di...