Jeff Phillips — accepted AI-conference papers

2023

Interpretable Debiasing of Vectorized Language Representations with Iterative Orthogonalization

Prince Osei Aboagye, Yan Zheng, Jack Shunn, Chin-Chia Michael Yeh, Junpeng Wang, Zhongfang Zhuang +4

ICLR 2023poster

We propose a new mechanism to augment a word vector embedding representation that offers improved bias removal while retaining the key information—resulting in improved interpretability of the representation. Rather than removing the information associated with a concept that may induce bias, our pr…

Cited by 7 Source ↗PDF ↗Scholar ↗

2022

Batch Multi-Fidelity Active Learning with Budget Constraints

Shibo Li, Jeff Phillips, Xin Yu, Robert Kirby, Shandian Zhe

NeurIPS 2022accept

Learning functions with high-dimensional outputs is critical in many applications, such as physical simulation and engineering design. However, collecting training examples for these applications is often costly, e.g., by running numerical solvers. The recent work (Li et al., 2022) proposes the firs…

Cited by 20 Source ↗PDF ↗Scholar ↗

2022

Normalization of Language Embeddings for Cross-Lingual Alignment

Prince Osei Aboagye, Yan Zheng, Chin-Chia Michael Yeh, Junpeng Wang, Wei Zhang, Liang Wang +2

ICLR 2022poster

Learning a good transfer function to map the word vectors from two languages into a shared cross-lingual word vector space plays a crucial role in cross-lingual NLP. It is useful in translation tasks and important in allowing complex models built on a high-resource language like English to be direct…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2021

A Deterministic Streaming Sketch for Ridge Regression

Benwei Shi, Jeff Phillips

AISTATS 2021poster

We provide a deterministic space-efficient algorithm for estimating ridge regression. For n data points with d features and a large enough regularization parameter, we provide a solution within eps L_2 error using only O(d/eps) space. This is the first o(d^2) space deterministic streaming algorithm…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2021

Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies

Sunipa Dev, Masoud Monajatipoor, Anaelia Ovalle, Arjun Subramonian, Jeff Phillips, Kai-Wei Chang

EMNLP 2021main

Gender is widely discussed in the context of language tasks and when examining the stereotypes propagated by language models. However, current discussions primarily treat gender as binary, which can perpetuate harms such as the cyclical erasure of non-binary gender identities. These harms are driven…

Cited by 185 Source ↗PDF ↗code ↗Scholar ↗

2021

Self-Adaptable Point Processes with Nonparametric Time Decays

Zhimeng Pan, Zheng Wang, Jeff Phillips, Shandian Zhe

NeurIPS 2021poster

Many applications involve multi-type event data. Understanding the complex influences of the events on each other is critical to discover useful knowledge and to predict future events and their types. Existing methods either ignore or partially account for these influences. Recent works use recurren…

Cited by 13 Source ↗PDF ↗Scholar ↗

2019

Attenuating Bias in Word vectors

Sunipa Dev, Jeff Phillips

AISTATS 2019poster

Word vector representations are well developed tools for various NLP and Machine Learning tasks and are known to retain significant semantic and syntactic structure of languages. But they are prone to carrying and amplifying bias which can perpetrate discrimination in various applications. In this w…

Cited by 185 Source ↗PDF ↗code ↗Scholar ↗

2016

Streaming Kernel Principal Component Analysis

Mina Ghashami, Daniel J. Perry, Jeff Phillips

AISTATS 2016poster

Kernel principal component analysis (KPCA) provides a concise set of basis vectors which capture non-linear structures within large data sets, and is a central tool in data analysis and learning. To allow for non-linear relations, typically a full n x n kernel matrix is constructed over n data poin…

Cited by 54 Source ↗PDF ↗Scholar ↗