Yaochu Jin

Sampled Training and Node Inheritance for Fast Evolutionary Neural Architecture Search

2020 · arXiv (Cornell University)

The performance of a deep neural network is heavily dependent on its architecture and various neural architecture search strategies have been developed for automated network architecture design. Recently, evolutionary neural architecture search (ENAS) has received …

Hybrid Attention-Based Transformer Block Model for Distant Supervision Relation Extraction

2020 · arXiv (Cornell University)

With an exponential explosive growth of various digital text information, it is challenging to efficiently obtain specific knowledge from massive unstructured text information. As one basic task for natural language processing (NLP), relation extraction aims …

Generation of consistent sets of multi-label classification rules with a multi-objective evolutionary algorithm

2020

Multi-label classification consists in classifying an instance into two or more classes simultaneously. Recently, the interest in interpretable classification models have grown, partially as a consequence of regulations such as the General Data Protection Regulation. …

A Recommender System for Metaheuristic Algorithms for Continuous Optimization Based on Deep Recurrent Neural Networks

2020 · IEEE Transactions on Artificial Intelligence

As revealed by the no free lunch theorem, no single algorithm can outperform any others on all classes of optimization problems. To tackle this issue, methods for recommending an existing algorithm for solving given problems …

Cooperative Coevolutionary CMA-ES With Landscape-Aware Grouping in Noisy Environments

2022 · IEEE Transactions on Evolutionary Computation

Many real-world optimization tasks suffer from noise. So far, the research on noise-tolerant optimization algorithms is still restricted to low-dimensional problems with less than 100 decision variables. In reality, many problems are high dimensional. Cooperative …

An Enhanced Differential Grouping Method for Large-Scale Overlapping Problems

2024 · arXiv (Cornell University)

Large-scale overlapping problems are prevalent in practical engineering applications, and the optimization challenge is significantly amplified due to the existence of shared variables. Decomposition-based cooperative coevolution (CC) algorithms have demonstrated promising performance in addressing large-scale …

Federated Incomplete Multi-View Clustering with Heterogeneous Graph Neural Networks

2024 · arXiv (Cornell University)

Federated multi-view clustering offers the potential to develop a global clustering model using data distributed across multiple devices. However, current methods face challenges due to the absence of label information and the paramount importance of …

Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models

2025 · arXiv (Cornell University)

Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak attacks often inject malicious instructions from text into less aligned modalities, such as vision. …

Artificial intelligence in recommender systems

2020 · Complex & Intelligent Systems

Abstract Recommender systems provide personalized service support to users by learning their previous behaviors and predicting their current preferences for particular products. Artificial intelligence (AI), particularly computational intelligence and machine learning methods and algorithms, has …