no code implementations • ICLR 2018 • Chen Wang, Xiangyu Chen, Zelin Ye, Jialu Wang, Ziruo Cai, Shixiang Gu, Cewu Lu
However, tasks with sparse rewards remain challenging when the state space is large.
no code implementations • 23 Jul 2018 • Ruijie Wang, Yuchen Yan, Jialu Wang, Yuting Jia, Ye Zhang, Wei-Nan Zhang, Xinbing Wang
Most existing knowledge graphs (KGs) in academic domains suffer from problems of insufficient multi-relational information, name ambiguity and improper data format for large-scale machine processing.
1 code implementation • 31 Oct 2020 • Jialu Wang, Yang Liu, Caleb Levy
We begin by presenting analytical results which show that naively imposing parity constraints on demographic disparity measures, without accounting for heterogeneous and group-dependent error rates, can decrease both the accuracy and the fairness of the resulting classifier.
no code implementations • 31 Oct 2020 • Yatong Chen, Jialu Wang, Yang Liu
Machine learning systems are often used in settings where individuals adapt their features to obtain a desired outcome.
no code implementations • Findings (ACL) 2022 • Jialu Wang, Yang Liu, Xin Eric Wang
To answer these questions, we view language as the fairness recipient and introduce two new fairness notions, multilingual individual fairness and multilingual group fairness, for pre-trained multimodal models.
1 code implementation • NeurIPS 2021 • Yang Liu, Jialu Wang
In this paper, we first quantify the trade-offs introduced by increasing a certain group of instances' label noise rate w. r. t.
1 code implementation • EMNLP 2021 • Jialu Wang, Yang Liu, Xin Eric Wang
Internet search affects people's cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good.
no code implementations • 5 Dec 2021 • Jialu Wang, Muhamad Risqi U. Saputra, Chris Xiaoxuan Lu, Niki Trigon, Andrew Markham
As a result, it learns to generate minimal image perturbations that are still capable of perplexing the network.
2 code implementations • 2 Feb 2022 • Zhaowei Zhu, Jialu Wang, Yang Liu
We observe that tasks with lower-quality features fail to meet the anchor-point or clusterability condition, due to the coexistence of both uninformative and informative representations.
1 code implementation • 31 May 2022 • Yatong Chen, Reilly Raab, Jialu Wang, Yang Liu
Given an algorithmic predictor that is "fair" on some source distribution, will it still be fair on an unknown target distribution that differs from the source within some bound?
1 code implementation • 30 Jun 2022 • Jialu Wang, Xin Eric Wang, Yang Liu
A variety of fairness constraints have been proposed in the literature to mitigate group-level statistical bias.
no code implementations • 28 Aug 2022 • Kaizhi Zheng, Kaiwen Zhou, Jing Gu, Yue Fan, Jialu Wang, Zonglin Di, Xuehai He, Xin Eric Wang
Building a conversational embodied agent to execute real-life tasks has been a long-standing yet quite challenging research goal, as it requires effective human-agent communication, multi-modal understanding, long-range sequential decision making, etc.
no code implementations • 10 Jan 2023 • Yingzhou Lu, Kosaku Sato, Jialu Wang
With the rise of internet technology amidst increasing rates of urbanization, sharing information has never been easier thanks to globally-adopted platforms for digital communication.
1 code implementation • 2 May 2023 • Zhen Zhang, Jialu Wang, Xin Eric Wang
Extensive experiments on XTD and Multi30K datasets, covering 11 languages under zero-shot, few-shot, and full-dataset learning scenarios, show that our framework significantly reduces the multilingual disparities among languages and improves cross-lingual transfer results, especially in low-resource scenarios, while only keeping and fine-tuning an extremely small number of parameters compared to the full model (e. g., Our framework only requires 0. 16\% additional parameters of a full-model for each language in the few-shot learning scenario).
no code implementations • 1 Jun 2023 • Jialu Wang, Xinyue Gabby Liu, Zonglin Di, Yang Liu, Xin Eric Wang
In this work, we seek to measure more complex human biases exist in the task of text-to-image generations.
1 code implementation • 5 Nov 2023 • Zeyu Tang, Jialu Wang, Yang Liu, Peter Spirtes, Kun Zhang
We reveal and address the frequently overlooked yet important issue of disguised procedural unfairness, namely, the potentially inadvertent alterations on the behavior of neutral (i. e., not problematic) aspects of data generating process, and/or the lack of procedural assurance of the greatest benefit of the least advantaged individuals.
1 code implementation • 19 Nov 2023 • Zhaowei Zhu, Jialu Wang, Hao Cheng, Yang Liu
Given the cost and difficulty of cleaning these datasets by humans, we introduce a systematic framework for evaluating the credibility of datasets, identifying label errors, and evaluating the influence of noisy labels in the curated language data, specifically focusing on unsafe comments and conversation classification.
no code implementations • 20 Feb 2024 • Jinlong Pang, Jialu Wang, Zhaowei Zhu, Yuanshun Yao, Chen Qian, Yang Liu
A fair classifier should ensure the benefit of people from different groups, while the group information is often sensitive and unsuitable for model training.
no code implementations • 22 Mar 2024 • Jialu Wang, Kaichen Zhou, Andrew Markham, Niki Trigoni
Despite the advancements in deep learning for camera relocalization tasks, obtaining ground truth pose labels required for the training process remains a costly endeavor.