Zheng Zhang

DGL-KE: Training Knowledge Graph Embeddings at Scale

2020 · arXiv (Cornell University)

Knowledge graphs have emerged as a key abstraction for organizing information in diverse domains and their embeddings are increasingly used to harness their information in various information retrieval and machine learning tasks. However, the ever …

Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks

2019 · arXiv (Cornell University)

Advancing research in the emerging field of deep graph learning requires new tools to support tensor computation over graphs. In this paper, we present the design principles and implementation of Deep Graph Library (DGL). DGL …

MDPL-net: Multi-layer Dictionary Learning Network with Added Skip Dense Connections

2020

Dictionary learning (DL) is powerful for representation learning, while it fails to capture the deep hierarchical information hidden in data. In this paper, we propose a new generalized end-to-end mulita-layer representation learning architecture referred to …

Towards Robust Neural Networks via Close-loop Control

2021 · International Conference on Learning Representations

Despite their success in massive engineering applications, deep neural networks are vulnerable to various perturbations due to their black-box nature. Recent study has shown that a deep neural network can misclassify the data even if …

Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing

2021 · arXiv (Cornell University)

Due to its powerful capability of representation learning and high-efficiency computation, deep hashing has made significant progress in large-scale image retrieval. However, deep hashing networks are vulnerable to adversarial examples, which is a practical secure …

A Unified Generative Framework for Aspect-Based Sentiment Analysis

2021 · arXiv (Cornell University)

Aspect-based Sentiment Analysis (ABSA) aims to identify the aspect terms, their corresponding sentiment polarities, and the opinion terms. There exist seven subtasks in ABSA. Most studies only focus on the subsets of these subtasks, which …

BLISS: Robust Sequence-to-Sequence Learning via Self-Supervised Input Representation

2022 · arXiv (Cornell University)

Data augmentations (DA) are the cores to achieving robust sequence-to-sequence learning on various natural language processing (NLP) tasks. However, most of the DA approaches force the decoder to make predictions conditioned on the perturbed input …

SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment Analysis

2022 · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Aspect-based Sentiment Analysis (ABSA) aims to predict the sentiment polarity towards a particular aspect in a sentence. Recently, graph neural networks based on dependency tree convey rich structural information which is proven to be utility …

GraphHINGE: Learning Interaction Models of Structured Neighborhood on Heterogeneous Information Network

2020 · arXiv (Cornell University)

Heterogeneous information network (HIN) has been widely used to characterize entities of various types and their complex relations. Recent attempts either rely on explicit path reachability to leverage path-based semantic relatedness or graph neighborhood to …

2EPV‐ApproCom: Enhanced Effective, Private, and Verifiable Approximate Similarity Computation with Server Aided over Scalable Datasets for IoT

2023 · Mathematical Problems in Engineering

In big data analytics, Jaccard similarity is a widely used block for scalable similarity computation. It is broadly applied in the Internet of Things (IoT) applications, such as credit system, social networking, epidemic tracking, and …

Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts

2023

As large language models (LLMs) have shown effectiveness with different prompting methods, such as Chain of Thought, Program of Thought, we find that these methods have formed a great complementarity to each other on math …

Distilling Large Language Models for Text-Attributed Graph Learning

2024 · arXiv (Cornell University)

Text-Attributed Graphs (TAGs) are graphs of connected textual documents. Graph models can efficiently learn TAGs, but their training heavily relies on human-annotated labels, which are scarce or even unavailable in many applications. Large language models …

Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective

2024 · arXiv (Cornell University)

Direct Preference Optimization (DPO), which derives reward signals directly from pairwise preference data, has shown its effectiveness on aligning Large Language Models (LLMs) with human preferences. Despite its widespread use across various tasks, DPO has …

A privacy-preserving location data collection framework for intelligent systems in edge computing

2024 · Ad Hoc Networks

With the rise of smart city applications, the accessibility of users’ location data by smart devices has increased significantly. However, this poses a privacy concern as attackers can deduce personal information from the raw location …

LLM for Complex Reasoning Task: An Exploratory Study in Fermi Problems

2025 · arXiv (Cornell University)

Fermi Problems (FPs) are mathematical reasoning tasks that require human-like logic and numerical reasoning. Unlike other reasoning questions, FPs often involve real-world impracticalities or ambiguous concepts, making them challenging even for humans to solve. Despite …

An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph

2020

There is an influx of heterogeneous information network (HIN) based recommender systems in recent years since HIN is capable of characterizing complex graphs and contains rich semantics. Although the existing approaches have achieved performance improvement, …