Liang Wang

Adaptive Pairwise Learning for Personalized Ranking with Content and Implicit Feedback

2015

Pairwise learning algorithms are a vital technique for personalized ranking with implicit feedback. They usually assume that each user is more interested in items which have been selected by the user than remaining ones. This …

An in-depth characterisation of Bots and Humans on Twitter

2017 · arXiv (Cornell University)

Recent research has shown a substantial active presence of bots in online social networks (OSNs). In this paper we utilise our past work on studying bots (Stweeler) to comparatively analyse the usage and impact of …

Evaluating Urban Sustainable Development Using Cloud Model

2017

Urban sustainable development is considered to be one of the most pressing issues in the world. In order to improve the ability of urban sustainable development, this study analyzes the influencing factors of urban sustainable …

Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning

2019 · Zurich Open Repository and Archive (University of Zurich)

Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and …

Leveraging User Profiling in Click-through Rate Prediction Based on Zhihu Data

2019

With the advent of the Web 2.0 era, the prediction of Click-through Rate (CTR) has been essential to improve the user experience and loyalty for the newly emerged industry, Content Marketing. Additionally, an incisive understanding …

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 …

Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation

2022 · arXiv (Cornell University)

Neural Machine Translation(NMT) models are usually trained via unidirectional decoder which corresponds to optimizing one-step-ahead prediction. However, this kind of unidirectional decoding framework may incline to focus on local structure rather than global coherence. To …

UKD: Debiasing Conversion Rate Estimation via Uncertainty-regularized Knowledge Distillation

2022 · arXiv (Cornell University)

In online advertising, conventional post-click conversion rate (CVR) estimation models are trained using clicked samples. However, during online serving the models need to estimate for all impression ads, leading to the sample selection bias (SSB) …

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 …

RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks

2022 · arXiv (Cornell University)

Temporal/spatial receptive fields of models play an important role in sequential/spatial tasks. Large receptive fields facilitate long-term relations, while small receptive fields help to capture the local details. Existing methods construct models with hand-designed receptive …

Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox

2022 · arXiv (Cornell University)

With the breakthrough of AlphaGo, deep reinforcement learning becomes a recognized technique for solving sequential decision-making problems. Despite its reputation, data inefficiency caused by its trial and error learning mechanism makes deep reinforcement learning hard …

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 …

PDT: Pretrained Dual Transformers for Time-aware Bipartite Graphs

2023 · arXiv (Cornell University)

Pre-training on large models is prevalent and emerging with the ever-growing user-generated content in many machine learning application categories. It has been recognized that learning contextual knowledge from the datasets depicting user-content interaction plays a …

The cognitive map and its intrinsic mechanisms

2023 · Advances in Psychological Science

摘要：

A Survey on Automatic Discover Approach by Using Static Analysis for Smart Contract Vulnerability

2023

Smart contract runs on blockchain platforms and plays a critical role in decentralized applications. Unfortunately, since smart contracts manage valuable digital assets, attacks against them can result in substantial economic losses. Especially, most of the …

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, $\textit {de facto}$ …

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.

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 …

C-DPSS: Channel dual-phase sparsity pruning framework for spiking neural networks

2026 · Neurocomputing

Spiking Neural Networks (SNNs) have emerged as an essential paradigm for brain-inspired computing, achieving superior energy efficiency on neuromorphic hardware. However, as network scale increases, SNNs encounter growing challenges in deployment efficiency. While structured pruning …

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 …

Session-Based Recommendation with Graph Neural Networks

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

The problem of session-based recommendation aims to predict user actions based on anonymous sessions. Previous methods model a session as a sequence and estimate user representations besides item representations to make recommendations. Though achieved promising …

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 Grammatical Error Correction via Pre-Training a Copy-Augmented Architecture with Unlabeled Data

2019

Wei Zhao, Liang Wang, Kewei Shen, Ruoyu Jia, Jingming Liu. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). …

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 …

Text Embeddings by Weakly-Supervised Contrastive Pre-training

2022 · arXiv (Cornell University)

This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale …