Philip S. Yu

Concurrent goal-oriented co-clustering generation in social networks

2015

Recent years, social network has attracted many attentions from research communities in data mining, social science and mobile etc, since users can create different types of information due to different actions and the information gives …

Disentangled Link Prediction for Signed Social Networks via Disentangled Representation Learning

2017

Link prediction is an important and interesting application for social networks because it can infer potential links among network participants. Existing approaches basically work with the homophily principle, i.e., people of similar characteristics tend to …

Improving automatic source code summarization via deep reinforcement learning

2018

Code summarization provides a high level natural language description of the function performed by code, as it can benefit the software maintenance, code categorization and retrieval. To the best of our knowledge, most state-of-the-art approaches …

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks

2018

Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks, where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph …

Securing Behavior-based Opinion Spam Detection

2018 · arXiv (Cornell University)

Reviews spams are prevalent in e-commerce to manipulate product ranking and customers decisions maliciously. While spams generated based on simple spamming strategy can be detected effectively, hardened spammers can evade regular detectors via more advanced …

Review Conversational Reading Comprehension

2019 · arXiv (Cornell University)

Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses. We first …

Utility Mining Across Multi-Dimensional Sequences

2019 · arXiv (Cornell University)

Knowledge extraction from database is the fundamental task in database and data mining community, which has been applied to a wide range of real-world applications and situations. Different from the support-based mining models, the utility-oriented …

Missing Movie Synergistic Completion across Multiple Isomeric Online Movie Knowledge Libraries.

2019 · arXiv (Cornell University)

Online knowledge libraries refer to the online data warehouses that systematically organize and categorize the knowledge-based information about different kinds of concepts and entities. In the era of big data, the setup of online knowledge …

Visual Domain Adaptation with Manifold Embedded Distribution Alignment

2018 · arXiv (Cornell University)

Visual domain adaptation aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Existing methods either attempt to align the cross-domain distributions, or perform manifold subspace learning. However, there …

Private Model Compression via Knowledge Distillation

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

The soaring demand for intelligent mobile applications calls for deploying powerful deep neural networks (DNNs) on mobile devices. However, the outstanding performance of DNNs notoriously relies on increasingly complex models, which in turn is associated …

JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation

2019 · arXiv (Cornell University)

Cross-domain recommendation can alleviate the data sparsity problem in recommender systems. To transfer the knowledge from one domain to another, one can either utilize the neighborhood information or learn a direct mapping function. However, all …

Partially Shared Adversarial Learning For Semi-supervised Multi-platform User Identity Linkage

2019

With the increasing popularity and diversity of social media, users tend to join multiple social platforms to enjoy different types of services. User identity linkage, which aims to link identical identities across different social platforms, …

Social-Aware VR Configuration Recommendation via Multi-Feedback Coupled Tensor Factorization

2019

Recent technological advent in virtual reality (VR) has attracted a lot of attention to the VR shopping, which thus far is designed for a single user. In this paper, we envision the scenario of VR …

Utility Mining across Multi-Sequences with Individualized Thresholds

2020 · ACM/IMS Transactions on Data Science

Utility-oriented pattern mining is an emerging topic, since it can reveal high-utility patterns from different types of data, which provides more information than the traditional frequency/confidence-based pattern mining models. The utilities of various items/objects are …

CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection

2020 · arXiv (Cornell University)

In this paper, we formulate a more realistic and difficult problem setup for the intent detection task in natural language understanding, namely Generalized Few-Shot Intent Detection (GFSID). GFSID aims to discriminate a joint label space …

BCFNet: A Balanced Collaborative Filtering Network with Attention Mechanism

2021 · arXiv (Cornell University)

Collaborative Filtering (CF) based recommendation methods have been widely studied, which can be generally categorized into two types, i.e., representation learning-based CF methods and matching function learning-based CF methods. Representation learning tries to learn a …

Outlier-Robust Multi-View Subspace Clustering with Prior Constraints

2021

Data may have multiple modalities, known as multi-view data. With the assumption that multi-view data often lie on a latent subspace, multi-view subspace clustering finds the underlying subspace by leveraging multiple views and clusters the …

Model-Based Self-Advising for Multi-Agent Learning

2022 · IEEE Transactions on Neural Networks and Learning Systems

In multiagent learning, one of the main ways to improve learning performance is to ask for advice from another agent. Contemporary advising methods share a common limitation that a teacher agent can only advise a …

G$^3$SR: Global Graph Guided Session-based Recommendation

2022 · arXiv (Cornell University)

Session-based recommendation tries to make use of anonymous session data to deliver high-quality recommendation under the condition that user-profiles and the complete historical behavioral data of a target user are unavailable. Previous works consider each …

A Generic Algorithm for Top-K On-Shelf Utility Mining

2022 · arXiv (Cornell University)

On-shelf utility mining (OSUM) is an emerging research direction in data mining. It aims to discover itemsets that have high relative utility in their selling time period. Compared with traditional utility mining, OSUM can find …

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations

2021 · arXiv (Cornell University)

Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real-life event descriptions is challenging because an …

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

2022 · arXiv (Cornell University)

Detecting which nodes in graphs are outliers is a relatively new machine learning task with numerous applications. Despite the proliferation of algorithms developed in recent years for this task, there has been no standard comprehensive …

Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks

2022 · arXiv (Cornell University)

Data augmentation techniques have been used to alleviate the problem of scarce labeled data in various NER tasks (flat, nested, and discontinuous NER tasks). Existing augmentation techniques either manipulate the words in the original text …

Learning from Atypical Behavior: Temporary Interest Aware Recommendation Based on Reinforcement Learning

2022 · arXiv (Cornell University)

Traditional robust recommendation methods view atypical user-item interactions as noise and aim to reduce their impact with some kind of noise filtering technique, which often suffers from two challenges. First, in real world, atypical interactions …

Towards Sequence Utility Maximization under Utility Occupancy Measure

2022 · arXiv (Cornell University)

The discovery of utility-driven patterns is a useful and difficult research topic. It can extract significant and interesting information from specific and varied databases, increasing the value of the services provided. In practice, the measure …

Think Rationally about What You See: Continuous Rationale Extraction for Relation Extraction

2023

Relation extraction (RE) aims to extract potential relations according to the context of two entities, thus, deriving rational contexts from sentences plays an important role. Previous works either focus on how to leverage the entity …

CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks

2023

While Chain-of-Thought prompting is popular in reasoning tasks, its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored. Motivated by multi-step reasoning of LLMs, we propose Coarse-to-Fine Chain-of-Thought (CoF-CoT) approach that …

Large Language Models Meet NLP: A Survey

2024 · arXiv (Cornell University)

While large language models (LLMs) like ChatGPT have shown impressive capabilities in Natural Language Processing (NLP) tasks, a systematic investigation of their potential in this field remains largely unexplored. This study aims to address this …

Zero-Shot Text Normalization via Cross-Lingual Knowledge Distillation

2024 · IEEE/ACM Transactions on Audio Speech and Language Processing

Text normalization (TN) is a crucial preprocessing step in text-to-speech synthesis, which pertains to the accurate pronunciation of numbers and symbols within the text. Existing neural network-based TN methods have shown significant success in rich-resource …

Personalized Multi-task Training for Recommender System

2024 · arXiv (Cornell University)

In the vast landscape of internet information, recommender systems (RecSys) have become essential for guiding users through a sea of choices aligned with their preferences. These systems have applications in diverse domains, such as news …

LEGO-Learn: Label-Efficient Graph Open-Set Learning

2024 · arXiv (Cornell University)

How can we train graph-based models to recognize unseen classes while keeping labeling costs low? Graph open-set learning (GOL) and out-of-distribution (OOD) detection aim to address this challenge by training models that can accurately classify …

Graph-Sequential Alignment and Uniformity: Toward Enhanced Recommendation Systems

2025

Graph-based and sequential methods are two popular recommendation paradigms, each excelling in its domain but lacking the ability to leverage signals from the other. To address this, we propose a novel method that integrates both …

Secure and Efficient Verification Protocol for Quantum Key Distribution

2025

Quantum key distribution (QKD) is a secure communication protocol that uses quantum bits (qubits) to ensure the security of key exchange between two entities (Alice and Bob). Their shared qubits may suffer from errors due …

AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

2025 · arXiv (Cornell University)

LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and adversarial collaboration. Existing defenses fall into two lines: (i) self-verification that …

GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning

2025 · arXiv (Cornell University)

The class imbalance problem refers to the disproportionate distribution of samples across different classes within a dataset, where the minority classes are significantly underrepresented. This issue is also prevalent in graph-structured data. Most graph neural …

Evolving Graph Learning for Out-of-Distribution Generalization in Non-Stationary Environments

2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Graph neural networks have shown remarkable success in exploiting the spatial and temporal patterns on dynamic graphs. However, existing GNNs exhibit poor generalization ability under distribution shifts, which is inevitable in dynamic scenarios. As dynamic …

Semantic Path based Personalized Recommendation on Weighted Heterogeneous Information Networks

2015

Recently heterogeneous information network (HIN) analysis has attracted a lot of attention, and many data mining tasks have been exploited on HIN. As an important data mining task, recommender system includes a lot of object …

Joint Deep Modeling of Users and Items Using Reviews for Recommendation

2017

A large amount of information exists in reviews written by users. This source of information has been ignored by most of the current recommender systems while it can potentially alleviate the sparsity problem and improve …

Serendipitous Recommendation in E-Commerce Using Innovator-Based Collaborative Filtering

2018 · IEEE Transactions on Cybernetics

Collaborative filtering (CF) algorithms have been widely used to build recommender systems since they have distinguishing capability of sharing collective wisdoms and experiences. However, they may easily fall into the trap of the Matthew effect, …

Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention Model

2018

Heterogeneous information network (HIN) has been widely adopted in recommender systems due to its excellence in modeling complex context information. Although existing HIN based recommendation methods have achieved performance improvement to some extent, they have …

Spectral collaborative filtering

2018

Despite the popularity of Collaborative Filtering (CF), CF-based methods are haunted by the cold-start problem, which has a significantly negative impact on users' experiences with Recommender Systems (RS). In this paper, to overcome the aforementioned …

Heterogeneous Information Network Embedding for Recommendation

2018 · IEEE Transactions on Knowledge and Data Engineering

Due to the flexibility in modelling data heterogeneity, heterogeneous information network (HIN) has been adopted to characterize complex and heterogeneous auxiliary data in recommender systems, calledHIN based recommendation. It is challenging to develop effective methods …

Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer

2021

In order to model the evolution of user preference, we should learn user/item embeddings based on time-ordered item purchasing sequences, which is defined as Sequential Recommendation~(SR) problem. Existing methods leverage sequential patterns to model item …

A Survey on Evaluation of Large Language Models

2024 · ACM Transactions on Intelligent Systems and Technology

Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, …