Qiang Liu

Probabilistic variational bounds for graphical models

2015 · neural information processing systems

Variational algorithms such as tree-reweighted belief propagation can provide deterministic bounds on the partition function, but are often loose and difficult to use in an fashion, expending more computation for tighter bounds. On the other …

Research on virtualized cloud forensics model and workflow

2015

As the cyber crimes are becoming increasingly rampant and indictable, the traditional digital forensics is no longer qualified in the more complex cloud computing environment. Due to the security issues and specific features of cloud …

FEPF: A knowledge Fusion and Evaluation Method based on Pagerank and Feature Selection

2020

In recent years, with the development of various knowledge bases, the fusion of multi-source knowledge bases is a hot and difficult problem facing the field of knowledge fusion. Due to the large differences in knowledge …

Deep Graph Structure Learning for Robust Representations: A Survey

2021

Graph Neural Networks (GNNs) are widely used for analyzing graph-structured data. Most GNN methods are highly sensitive to the quality of graph structures and usually require a perfect graph structure for learning informative embeddings. However, …

Disentangled Item Representation for Recommender Systems

2021 · ACM Transactions on Intelligent Systems and Technology

Item representations in recommendation systems are expected to reveal the properties of items. Collaborative recommender methods usually represent an item as one single latent vector. Nowadays the e-commercial platforms provide various kinds of attribute information …

A Competence-Based Three-Layer Cybersecurity Education Framework and Its Application

2021

The Computing Curricula 2020 (CC2020) competence model raises a big challenge to cybersecurity education in terms of knowledge, skill and disposition. In this paper, we propose a competence-based three-layer cybersecurity education framework using an ensembling …

Dynamic Graph Neural Networks for Sequential Recommendation

2021 · arXiv (Cornell University)

Modeling user preference from his historical sequences is one of the core problems of sequential recommendation. Existing methods in this field are widely distributed from conventional methods to deep learning methods. However, most of them …

Uncertainty Estimation Based Doubly Robust Learning for Debiasing Recommendation

2022 · 2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)

In recommender systems, the interactions between users and items are sparse, which means most of the interactions between users and items are missing. More importantly, the loss of these interactions is non-random, which leads to …

LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

2023 · arXiv (Cornell University)

Large language models (LLMs) have demonstrated remarkable zero-shot generalization abilities: state-of-the-art chatbots can provide plausible answers to many common questions that arise in daily life. However, so far, LLMs cannot reliably solve long-horizon planning problems. …

Ensuring User Privacy and Model Security via Machine Unlearning: A Review

2023 · Computers, materials & continua/Computers, materials & continua (Print)

As an emerging discipline, machine learning has been widely used in artificial intelligence, education, meteorology and other fields. In the training of machine learning models, trainers need to use a large amount of practical data, …

Uncovering Overfitting in Large Language Model Editing

2024 · arXiv (Cornell University)

Knowledge editing has been proposed as an effective method for updating and correcting the internal knowledge of Large Language Models (LLMs). However, existing editing methods often struggle with complex tasks, such as multi-hop reasoning. In …

Beyond Filtering: Adaptive Image-Text Quality Enhancement for MLLM Pretraining

2024 · arXiv (Cornell University)

Multimodal large language models (MLLMs) have made significant strides by integrating visual and textual modalities. A critical factor in training MLLMs is the quality of image-text pairs within multimodal pretraining datasets. However, $\textit {de facto}$ …

Photonic diffractive generators through sampling noises from scattering media

2024 · Nature Communications

Photonic computing, with potentials of high parallelism, low latency and high energy efficiency, have gained progressive interest at the forefront of neural network (NN) accelerators. However, most existing photonic computing accelerators concentrate on discriminative NNs. …

Personalized Text Generation with Contrastive Activation Steering

2025

Jinghao Zhang, Yuting Liu, Wenjie Wang, Qiang Liu, Shu Wu, Liang Wang, Tat-Seng Chua. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Exploring illicit personal information trading behind telecom fraud in China

2025 · Humanities and Social Sciences Communications

Illicit personal information trading, a hallmark of internet dark and gray industries, has deeply infiltrated the global criminal economic system, serving as a critical driver and “raw material factory” for numerous offenses. This study focuses …

SEEM: Exploiting Black-Box Text Attacks to Manipulate Tool Selection

2025 · ArXiv.org

Tool learning has emerged as a powerful auxiliary mechanism that extends the capabilities of large language models (LLMs), enabling them to address complex tasks that demand real-time relevance or high-precision operations. However, beneath this strength …

A Dynamic Recurrent Model for Next Basket Recommendation

2016

Next basket recommendation becomes an increasing concern. Most conventional models explore either sequential transaction features or general interests of users. Further, some works treat users' general interests and sequential behaviors as two totally divided matters, …

Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

Spatial and temporal contextual information plays a key role for analyzing user behaviors, and is helpful for predicting where he or she will go next. With the growing ability of collecting information, more and more …

DeepStyle

2017

Visual information is an important factor in recommender systems. Some studies have been done to model user preferences for visual recommendation. Usually, an item consists of two fundamental components: style and category. Conventional methods model …

MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation

2018 · IEEE Transactions on Knowledge and Data Engineering

Sequential recommendation is a fundamental task for network applications, and it usually suffers from the item cold start problem due to the insufficiency of user feedbacks. There are currently three kinds of popular approaches which …

Improving Neural Language Modeling via Adversarial Training

2019 · arXiv (Cornell University)

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present …

Context-Aware Sequential Recommendation

2016

Since sequential information plays an important role in modeling user behaviors, various sequential recommendation methods have been proposed. Methods based on Markov assumption are widely-used, but independently combine several most recent components. Recently, Recurrent Neural …

Deep Graph Contrastive Representation Learning

2020 · arXiv (Cornell University)

Graph representation learning nowadays becomes fundamental in analyzing graph-structured data. Inspired by recent success of contrastive methods, in this paper, we propose a novel framework for unsupervised graph representation learning by leveraging a contrastive objective …

Graph Contrastive Learning with Adaptive Augmentation

2021

Recently, contrastive learning (CL) has emerged as a successful method for unsupervised graph representation learning. Most graph CL methods first perform stochastic augmentation on the input graph to obtain two graph views and maximize the …