Xia Hu

Towards Explanation of DNN-based Prediction with Guided Feature Inversion

2018

While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics. Existing attempts …

PyODDS: An End-to-end Outlier Detection System with Automated Machine Learning

2020 · Companion Proceedings of the Web Conference 2020

Outlier detection is an important task for various data mining applications. Current outlier detection techniques are often manually designed for specific domains, requiring large human efforts of database setup, algorithm selection, and hyper-parameter tuning. To …

Deep Serial Number: Computational Watermarking for DNN Intellectual Property Protection

2020 · arXiv (Cornell University)

In this paper, we present DSN (Deep Serial Number), a simple yet effective watermarking algorithm designed specifically for deep neural networks (DNNs). Unlike traditional methods that incorporate identification signals into DNNs, our approach explores a …

DivAug: Plug-in Automated Data Augmentation with Explicit Diversity Maximization

2021 · arXiv (Cornell University)

Human-designed data augmentation strategies have been replaced by automatically learned augmentation policy in the past two years. Specifically, recent work has empirically shown that the superior performance of the automated data augmentation methods stems from …

Towards Personalized Preprocessing Pipeline Search

2023 · arXiv (Cornell University)

Feature preprocessing, which transforms raw input features into numerical representations, is a crucial step in automated machine learning (AutoML) systems. However, the existing systems often have a very small search space for feature preprocessing with …

CoRTX: Contrastive Framework for Real-time Explanation

2023 · arXiv (Cornell University)

Recent advancements in explainable machine learning provide effective and faithful solutions for interpreting model behaviors. However, many explanation methods encounter efficiency issues, which largely limit their deployments in practical scenarios. Real-time explainer (RTX) frameworks have …

PME: pruning-based multi-size embedding for recommender systems

2023 · Frontiers in Big Data

Embedding is widely used in recommendation models to learn feature representations. However, the traditional embedding technique that assigns a fixed size to all categorical features may be suboptimal due to the following reasons. In recommendation …

Content-Aware Point of Interest Recommendation on Location-Based Social Networks

2015 · Proceedings of the AAAI Conference on Artificial Intelligence

The rapid urban expansion has greatly extended the physical boundary of users' living area and developed a large number of POIs (points of interest). POI recommendation is a task that facilitates users' urban exploration and …

Recommendation with Social Dimensions

2016 · Proceedings of the AAAI Conference on Artificial Intelligence

The pervasive presence of social media greatly enriches online users' social activities, resulting in abundant social relations. Social relations provide an independent source for recommendation, bringing about new opportunities for recommender systems. Exploiting social relations …

Label Informed Attributed Network Embedding

2017

Attributed network embedding aims to seek low-dimensional vector representations for nodes in a network, such that original network topological structure and node attribute proximity can be preserved in the vectors. These learned representations have been …

Neural Collaborative Filtering

2017 · arXiv (Cornell University)

In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. However, the exploration of deep neural networks on recommender systems has received relatively less scrutiny. In …

Fairness-Aware Tensor-Based Recommendation

2018

Tensor-based methods have shown promise in improving upon traditional matrix factorization methods for recommender systems. But tensors may achieve improved recommendation quality while worsening the fairness of the recommendations. Hence, we propose a novel fairness-aware …