Xin Liu

A Memory Allocation Model for Cassandra Database

2016 · Advanced science and technology letters

Cassandra database system is one of the universal databases. To achieve high performance, we should allocate memory space rationally according to actual demands. To solve this problem, we firstly analyze the reading and writing process …

Learning User Dependencies for Recommendation

2017

Social recommender systems exploit users' social relationships to improve recommendation accuracy. Intuitively, a user tends to trust different people regarding with different scenarios. Therefore, one main challenge of social recommendation is to exploit the most …

he Teaching Reform of Data Structure Centered on the Cultivation of Innovation Ability: Taking Local Undergraduate College as an Example

2018 · Proceedings of the 2018 3rd International Conference on Humanities Science, Management and Education Technology (HSMET 2018)

Data Structure is the core course of the major of computer science and technology, and it plays an important role in cultivating students' creation ability. Firstly, the present situation of Data Structure teaching was analyzed. …

Efficient Path Prediction for Semi-Supervised and Weakly Supervised Hierarchical Text Classification

2019

Hierarchical text classification has many real-world applications. However, labeling a large number of documents is costly. In practice, we can use semi-supervised learning or weakly supervised learning (e.g., dataless classification) to reduce the labeling cost. …

Gated Semantic Difference Based Sentence Semantic Equivalence Identification

2020 · IEEE/ACM Transactions on Audio Speech and Language Processing

This article proposes a novel sentence semantic equivalence identification (SSEI) method by using the semantic difference features between sentences. The lexical differences of a sentence pair are first extracted, and the bidirectional long short term …

OAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space

2021 · arXiv (Cornell University)

Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, contains a lot of different features …

Ethereum Fraud Detection with Heterogeneous Graph Neural Networks

2022 · arXiv (Cornell University)

While transactions with cryptocurrencies such as Ethereum are becoming more prevalent, fraud and other criminal transactions are not uncommon. Graph analysis algorithms and machine learning techniques detect suspicious transactions that lead to phishing in large …

Teaching and Development Ideas of Double-row Keyboard Electronic Organ in Colleges and Universities

2019

The double-row keyboard electronic organ is different from other musical instruments. It is a comprehensive and expressive electronic instrument. It not only brings people good enjoyment, but also opens up the field of expression of …

A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes

2022 · Proceedings of the AAAI Conference on Artificial Intelligence

This paper presents a model-free reinforcement learning (RL) algorithm for infinite-horizon average-reward Constrained Markov Decision Processes (CMDPs). Considering a learning horizon K, which is sufficiently large, the proposed algorithm achieves sublinear regret and zero constraint …

KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation

2021 · arXiv (Cornell University)

Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since sentences they produce are …

Neural Network Optimization Objective Vector Representation based on Genetic Algorithm and Its Multi-objective Optimization Method

2023

Deep learning algorithms mostly have network parameters that can affect their training results, and the combination of neural network architectures also has a significant impact on the algorithm performance. The performance of deep learning algorithms …

A New Safe-Level Enabled Borderline-SMOTE for Condition Recognition of Imbalanced Dataset

2023 · IEEE Transactions on Instrumentation and Measurement

Machine learning-based classification strategy has been successfully applied in actual industrial monitoring but it is often hindered when the data set is imbalanced. Technically, the misclassification phenomenon, as a serious performance degradation of generalisation ability, …

Gentopia: A Collaborative Platform for Tool-Augmented LLMs

2023 · arXiv (Cornell University)

Augmented Language Models (ALMs) empower large language models with the ability to use tools, transforming them into intelligent agents for real-world interactions. However, most existing frameworks for ALMs, to varying degrees, are deficient in the …

AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph

2023 · arXiv (Cornell University)

Cognitive research indicates that abstraction ability is essential in human intelligence, which remains under-explored in language models. In this paper, we present AbsPyramid, a unified entailment graph of 221K textual descriptions of abstraction knowledge. While …

Novel MITM attack scheme based on built-in negotiation for blockchain-based digital twins

2023 · Digital Communications and Networks

As smart contracts, represented by Solidity, become deeply integrated into the manufacturing industry, blockchain-based Digital Twins (DT) has gained momentum in recent years. Most of the blockchain infrastructures in widespread use today are based on …

Fast Adversarial Training against Textual Adversarial Attacks

2024 · arXiv (Cornell University)

Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates used by attackers …

AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation

2024 · arXiv (Cornell University)

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. In this …

Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection

2024 · arXiv (Cornell University)

Graph-based anomaly detection is currently an important research topic in the field of graph neural networks (GNNs). We find that in graph anomaly detection, the homophily distribution differences between different classes are significantly greater than …

EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model

2024 · arXiv (Cornell University)

Emotion AI is the ability of computers to understand human emotional states. Existing works have achieved promising progress, but two limitations remain to be solved: 1) Previous studies have been more focused on short sequential …

FGP-GAN: Fine-Grained Perception Integrated Generative Adversarial Network for Expressive Mandarin Singing Voice Synthesis

2024 · IEEE Transactions on Consumer Electronics

Though singing voice synthesis (SVS) has been explored by recent works, pitch over-smoothing and spectral blurring are still unresolved, resulting in lack of expressiveness of the singing voice. To tackle the afore-mentioned problems, an SVS …

Short-Term Photovoltaic System Output Power Prediction Based on Integrated Deep Learning Algorithms in the Clean Energy Sector

2024 · International Journal of e-Collaboration

Photovoltaic power generation system plays an important role in renewable energy. Therefore, accurately predicting the short-term output power of photovoltaic system has become a key challenge for real-time power grid management. This study focuses on …

How Powerful is Graph Filtering for Recommendation

2024

It has been shown that the effectiveness of graph convolutional network (GCN) for recommendation is attributed to the spectral graph filtering. Most GCN-based methods consist of a graph filter or followed by a low-rank mapping …

Exploring the Chameleon Effect of Contextual Dynamics in Temporal Knowledge Graph for Event Prediction

2024 · Tsinghua Science & Technology

The ability to forecast future events brings great benefits for society and cyberspace in many public safety domains, such as civil unrest, pandemics and crimes. The occurrences of new events are often correlated or dependent …

CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning

2024

Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Cheng Jiayang, Chunkit Chan, Yangqiu Song. Proceedings of the 62nd Annual Meeting of the Association for Computational …

MU-MAE: Multimodal Masked Autoencoders-Based One-Shot Learning

2024

With the exponential growth of multimedia data, leveraging multimodal sensors presents a promising approach for improving accuracy in human activity recognition. Nevertheless, accurately identifying these activities using both video data and wearable sensor data presents …

Beyond Label: Cold-Start Self-Training for Cross-Domain Semantic Text Similarity

2024

In Natural Language Processing (NLP), comprehending the semantic connection between two texts, a Semantic Text Similarity (STS) task, poses a significant challenge. This challenge is especially pronounced in resource-constrained and cross-domain contexts, where traditional methods …

Diagnosis of Major Depressive Disorder Based on Anomaly Detection with sMRI Gray Matter Slices

2024

The current research focus on Major Depressive Disorder (MDD) is a reflection of its significant adverse impact on individuals and society. Structural magnetic resonance imaging (SMRI) is a valuable tool for clinicians in diagnosing and …

LCQMC:A Large-scale Chinese Question Matching Corpus

2018 · International Conference on Computational Linguistics

The lack of large-scale question matching corpora greatly limits the development of matching methods in question answering (QA) system, especially for non-English languages. To ameliorate this situation, in this paper, we introduce a large-scale Chinese …

The BQ Corpus: A Large-scale Domain-specific Chinese Corpus For Sentence Semantic Equivalence Identification

2018

This paper introduces the Bank Question (BQ) corpus, a Chinese corpus for sentence semantic equivalence identification (SSEI). The BQ corpus contains 120,000 question pairs from 1-year online bank custom service logs. To efficiently process and …