Search Results for author: Haochen Liu

Found 13 papers, 4 papers with code

Trustworthy AI: A Computational Perspective

no code implementations12 Jul 2021 Haochen Liu, Yiqi Wang, Wenqi Fan, Xiaorui Liu, Yaxin Li, Shaili Jain, Yunhao Liu, Anil K. Jain, Jiliang Tang

In the past few decades, artificial intelligence (AI) technology has experienced swift developments, changing everyone's daily life and profoundly altering the course of human society.

Fairness

AutoLoss: Automated Loss Function Search in Recommendations

no code implementations12 Jun 2021 Xiangyu Zhao, Haochen Liu, Wenqi Fan, Hui Liu, Jiliang Tang, Chong Wang

Unlike existing algorithms, the proposed controller can adaptively generate the loss probabilities for different data examples according to their varied convergence behaviors.

Recommendation Systems

The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification

no code implementations Findings (ACL) 2021 Haochen Liu, Wei Jin, Hamid Karimi, Zitao Liu, Jiliang Tang

The results show that the text classification models trained under our proposed framework outperform traditional models significantly in terms of fairness, and also slightly in terms of classification performance.

Classification Fairness +2

Personalized Multimodal Feedback Generation in Education

no code implementations COLING 2020 Haochen Liu, Zitao Liu, Zhongqin Wu, Jiliang Tang

The automatic evaluation for school assignments is an important application of AI in the education field.

Text Generation

Mitigating Gender Bias for Neural Dialogue Generation with Adversarial Learning

1 code implementation EMNLP 2020 Haochen Liu, Wentao Wang, Yiqi Wang, Hui Liu, Zitao Liu, Jiliang Tang

Extensive experiments on two real-world conversation datasets show that our framework significantly reduces gender bias in dialogue models while maintaining the response quality.

Dialogue Generation

Memory-efficient Embedding for Recommendations

no code implementations26 Jun 2020 Xiangyu Zhao, Haochen Liu, Hui Liu, Jiliang Tang, Weiwei Guo, Jun Shi, Sida Wang, Huiji Gao, Bo Long

Specifically, we first proposed an end-to-end differentiable framework that can calculate the weights over various dimensions for feature fields in a soft and continuous manner with an AutoML based optimization algorithm; then we derive a hard and discrete embedding component architecture according to the maximal weights and retrain the whole recommender framework.

AutoML Recommendation Systems

Chat as Expected: Learning to Manipulate Black-box Neural Dialogue Models

no code implementations27 May 2020 Haochen Liu, Zhiwei Wang, Tyler Derr, Jiliang Tang

Recently, neural network based dialogue systems have become ubiquitous in our increasingly digitalized society.

Does Gender Matter? Towards Fairness in Dialogue Systems

1 code implementation COLING 2020 Haochen Liu, Jamell Dacon, Wenqi Fan, Hui Liu, Zitao Liu, Jiliang Tang

In particular, we construct a benchmark dataset and propose quantitative measures to understand fairness in dialogue models.

Fairness

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

4 code implementations17 Sep 2019 Han Xu, Yao Ma, Haochen Liu, Debayan Deb, Hui Liu, Jiliang Tang, Anil K. Jain

In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i. e., images, graphs and text.

Adversarial Attack

Say What I Want: Towards the Dark Side of Neural Dialogue Models

no code implementations13 Sep 2019 Haochen Liu, Tyler Derr, Zitao Liu, Jiliang Tang

Neural dialogue models have been widely adopted in various chatbot applications because of their good performance in simulating and generalizing human conversations.

Chatbot

Cannot find the paper you are looking for? You can Submit a new open access paper.