Xiang Li

Maximum Likelihood Estimation for Single Linkage Hierarchical Clustering

2015 · arXiv (Cornell University)

We derive a statistical model for estimation of a dendrogram from single linkage hierarchical clustering (SLHC) that takes account of uncertainty through noise or corruption in the measurements of separation of data. Our focus is …

DHS

2021

Data stream processing is a crucial computation task in data mining applications. The rigid and fixed data structures in existing solutions limit their accuracy, throughput, and generality in measurement tasks. We propose Dynamic Hierarchical Sketch …

A Lightweight Attribute-Based Access Control Scheme for Intelligent Transportation System With Full Privacy Protection

2020 · IEEE Sensors Journal

The Intelligent Transportation System (ITS) provides more possibilities for the realization of smart cities by integrating the Internet of Things (IoT) and cloud computing. However, how to ensure security of IoT data stored in the …

A study of individual identification of radiation source based on feature extraction and deep learning

2021 · Journal of Physics Conference Series

Abstract Emitter identification technology can distinguish the types of radiation sources and identify the identity of emitter. It has broad application prospects in both military and civilian fields. The article mainly reviews the radiation source …

A modified biogeography‐based optimization algorithm based on cloud theory for optimizing a fuzzy <scp>PID</scp> controller

2022 · Optimal Control Applications and Methods

Abstract In recent years, the heuristic algorithms used to improve the PID controller have attracted increasing attention. Additionally, there have been many significative explorations into the field of the fuzzy PID controller. Therefore, this article …

Joint Learning of E-commerce Search and Recommendation with a Unified Graph Neural Network

2022 · Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

Click-through rate (CTR) prediction plays an important role in search and recommendation, which are the two most prominent scenarios in e-commerce. A number of models have been proposed to predict CTR by mining user behaviors, …

An End-to-end Chinese Text Normalization Model based on Rule-guided Flat-Lattice Transformer

2022 · arXiv (Cornell University)

Text normalization, defined as a procedure transforming non standard words to spoken-form words, is crucial to the intelligibility of synthesized speech in text-to-speech system. Rule-based methods without considering context can not eliminate ambiguation, whereas sequence-to-sequence …

Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding

2022 · arXiv (Cornell University)

Knowledge-enhanced Pre-trained Language Model (PLM) has recently received significant attention, which aims to incorporate factual knowledge into PLMs. However, most existing methods modify the internal structures of fixed types of PLMs by stacking complicated modules, …

Hierarchical Information Fusion Graph Neural Networks for Chinese Implicit Rhetorical Questions Recognition

2022 · 2022 International Joint Conference on Neural Networks (IJCNN)

The rhetorical question is a commonly used rhetorical technique in modern Chinese. It can be divided into explicit rhetorical questions and implicit rhetorical questions according to whether it contains rhetorical cues. The implicit rhetorical questions …

A Security Protection Technology Based on Multi-factor Authentication

2022 · 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC)

Today, with the rapid development of the information society and the increasingly complex computer network environment, multi-factor authentication, as one of the security protection technologies, plays an important role in both IT science and business. …

GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting

2023 · arXiv (Cornell University)

Federated Learning (FL) has emerged as a de facto machine learning area and received rapid increasing research interests from the community. However, catastrophic forgetting caused by data heterogeneity and partial participation poses distinctive challenges for …

Disentangled and Robust Representation Learning for Bragging Classification in Social Media

2023

Researching bragging behavior on social media arouses interest of computational (socio) linguists. However, existing bragging classification datasets suffer from a serious data imbalance issue. Because labeling a data-balance dataset is expensive, most methods introduce external …

ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs

2023 · arXiv (Cornell University)

ChatGPT, as a recently launched large language model (LLM), has shown superior performance in various natural language processing (NLP) tasks. However, two major limitations hinder its potential applications: (1) the inflexibility of finetuning on downstream …

UPFL: Unsupervised Personalized Federated Learning towards New Clients

2023 · arXiv (Cornell University)

Personalized federated learning has gained significant attention as a promising approach to address the challenge of data heterogeneity. In this paper, we address a relatively unexplored problem in federated learning. When a federated model has …

Ranking-Enhanced Unsupervised Sentence Representation Learning

2023

Yeon Seonwoo, Guoyin Wang, Changmin Seo, Sajal Choudhary, Jiwei Li, Xiang Li, Puyang Xu, Sunghyun Park, Alice Oh. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data

2023 · arXiv (Cornell University)

Recently, the utilization of extensive open-sourced text data has significantly advanced the performance of text-based large language models (LLMs). However, the use of in-the-wild large-scale speech data in the speech technology community remains constrained. One …

Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes

2023 · arXiv (Cornell University)

Heterogeneous Information Networks (HINs), which consist of various types of nodes and edges, have recently demonstrated excellent performance in graph mining. However, most existing heterogeneous graph neural networks (HGNNs) ignore the problems of missing attributes, …

Manufacturing Companies Financial Fraud Detection Based on Interpretable Machine Learning

2023

Because of the industrial characteristics like complex purchasing and selling links in manufacturing companies, it is relatively easy for them to conduct financial fraud. Taking A-share manufacturing companies from 2009 to 2021 as an observation …

A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions

2024 · arXiv (Cornell University)

Graphs are structured data that models complex relations between real-world entities. Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar features, have recently attracted significant attention and found many real-world …

Track - Before- Detect Labeled Multi - Bernoulli Filter for Multi- Target Bearing-Only Tracking using an Autonomous Underwater Vehicle

2024

This paper considers an autonomous underwater vehicle (AUV) mounted with an array of sensors to detect the presence of multiple targets and estimate their relative locations. We propose a track-before-detect labeled multi-Bernoulli filter, which directly …

OGSS: An Ontology-Guided and Scheduled-Sampling Approach for Overlapping Event Extraction

2024 · Symmetry

Event extraction is a complex and challenging task in the field of information extraction. It aims to identify event types, triggers, and argument information from the text. In recent years, overlapping event extraction has attracted …

RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning

2024 · arXiv (Cornell University)

The advent of the "pre-train, prompt" paradigm has recently extended its generalization ability and data efficiency to graph representation learning, following its achievements in Natural Language Processing (NLP). Initial graph prompt tuning approaches tailored specialized …

Hierarchical Conditional Multi-Task Learning for Streamflow Modeling

2024 · arXiv (Cornell University)

Streamflow, vital for water resource management, is governed by complex hydrological systems involving intermediate processes driven by meteorological forces. While deep learning models have achieved state-of-the-art results of streamflow prediction, their end-to-end single-task learning approach …

Advancing Textual Prompt Learning with Anchored Attributes

2024 · arXiv (Cornell University)

Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current training …

Aligning Explanations for Recommendation with Rating and Feature via Maximizing Mutual Information

2024 · arXiv (Cornell University)

Providing natural language-based explanations to justify recommendations helps to improve users' satisfaction and gain users' trust. However, as current explanation generation methods are commonly trained with an objective to mimic existing user reviews, the generated …

Learning Prioritized Node-Wise Message Propagation in Graph Neural Networks (Extended Abstract)

2025

Graphs are ubiquitous in the real world, in graphs, nodes represent entities and edges capture their relationships. Recently, graph neural networks (GNNs) [3]–[6] have been proposed to integrate these two sources of information. In GNNs, …

Hybrid CNN-Mamba Enhancement Network for Robust Multimodal Sentiment Analysis

2025 · arXiv (Cornell University)

Multimodal Sentiment Analysis (MSA) with missing modalities has recently attracted increasing attention. Although existing research mainly focuses on designing complex model architectures to handle incomplete data, it still faces significant challenges in effectively aligning and …

A Vision for Auto Research with LLM Agents

2025 · arXiv (Cornell University)

This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Leveraging the capabilities of large language models (LLMs) and modular agent collaboration, the …

Commonsense Knowledge Base Completion

2016

We enrich a curated resource of commonsense knowledge by formulating the problem as one of knowledge base completion (KBC). Most work in KBC focuses on knowledge bases like Freebase that relate entities drawn from a …

Learning Tree-based Deep Model for Recommender Systems

2018

Model-based methods for recommender systems have been studied extensively in recent years. In systems with large corpus, however, the calculation cost for the learnt model to predict all user-item preferences is tremendous, which makes full …

Disentangling User Interest and Conformity for Recommendation with Causal Embedding

2021

Recommendation models are usually trained on observational interaction data. However, observational interaction data could result from users’ conformity towards popular items, which entangles users’ real interest. Existing methods tracks this problem as eliminating popularity bias, …