Debiasing knowledge graph embeddings

Fisher, Joseph B.; Mittal, Arpit; Palfrey, Dave; Christodoulopoulos, Christos

doi:10.18653/v1/2020.emnlp-main.595

Cited by 39 publications

(37 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparison with adversarial debiasing and regularization. To validate the effectiveness of proposed FMP, we also show the prediction performance and fairness metric trade-off compared with fairness-boosting methods, including adversarial debiasing (Fisher et al, 2020) and adding regularization (Chuang & Mroueh, 2020). Similar to (Louppe et al, 2017), the output of GNNs is the input of adversary and the goal of adversary is to predict the node sensitive attribute.…”

Section: Resultsmentioning

confidence: 99%

“…A pilot study on fair node representation learning is developed based on random walk (Rahman et al, 2019). Additionally, adversarial debiasing is adopt to learn fair prediction or node representation so that the well-trained adversary can not predict the sensitvie attribute based on node representation or prediction (Dai & Wang, 2021;Bose & Hamilton, 2019;Fisher et al, 2020). A Bayesian approach is developed to learn fair node representation via encoding sensitive information in prior distribution in (Buyl & De Bie, 2020).…”

Section: J Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FMP: Toward Fair Graph Message Passing against Topology Bias

Jiang¹,

Han²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Despite recent advances in achieving fair representations and predictions through regularization, adversarial debiasing, and contrastive learning in graph neural networks (GNNs), the working mechanism (i.e., message passing) behind GNNs inducing unfairness issue remains unknown. In this work, we theoretically and experimentally demonstrate that representative aggregation in message passing schemes accumulates bias in node representation due to topology bias induced by graph topology. Thus, a Fair Message Passing (FMP) scheme is proposed to aggregate useful information from neighbors but minimize the effect of topology bias in a unified framework considering graph smoothness and fairness objectives. The proposed FMP is effective, transparent, and compatible with back-propagation training. An acceleration approach on gradient calculation is also adopted to improve algorithm efficiency. Experiments on node classification tasks demonstrate that the proposed FMP outperforms the state-ofthe-art baselines in effectively and efficiently mitigating bias on three real-world datasets.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: J Related Workmentioning

confidence: 99%

FMP: Toward Fair Graph Message Passing against Topology Bias

Jiang¹,

Han²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…(Shankar et al 2017) show population / representation bias existing in OpenImages and Im-ageNet. (Fisher et al 2019) showed web-scale commonsense KGs can be tough to curate and can allow biases to creep in. (Janowicz et al 2018) note how the density of world locations generating DBPedia data (extracted from Wikipedia) is at odds with world population density.…”

Section: Ethical Impactmentioning

confidence: 99%

Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings

Ramnath¹,

Hasegawa‐Johnson²

2020

Preprint

View full text Add to dashboard Cite

Fact-based Visual Question Answering (FVQA), a challenging variant of VQA, requires a QA-system to include facts from a diverse knowledge graph (KG) in its reasoning process to produce an answer. Large KGs, especially commonsense KGs, are known to be incomplete, i.e. not all non-existent facts are always incorrect. Therefore, being able to reason over incomplete KGs for QA is a critical requirement in realworld applications that has not been addressed extensively in the literature. We develop a novel QA architecture that allows us to reason over incomplete KGs, something current FVQA state-of-the-art (SOTA) approaches lack. We use KG Embeddings, a technique widely used for KG completion, for the downstream task of FVQA. We also employ a new image representation technique we call 'Image-as-Knowledge' to enable this capability, alongside a simple one-step co-Attention mechanism to attend to text and image during QA. Our FVQA architecture is faster during inference time, being O(m), as opposed to existing FVQA SOTA methods which are O(N logN ), where m = number of vertices, N = number of edges = O(m 2 ). We observe that our architecture performs comparably in the standard answer-retrieval baseline with existing methods; while for missing-edge reasoning, our KG representation outperforms the SOTA representation by 25%, and image representation outperforms the SOTA representation by 2.6%. The primary contribution of this paper is a method that permits FVQA to reason about common-sense facts that are absent from the knowledge graph (missing edges). KG embeddings permits us to offer two additional contributions to the SOTA in FVQA: an 'image-as-knowledge' representation of visual information, and a coAttention method for combining visual and textual inputs. 'Image-as-knowledge' represents the image as the span of the KG embedding vectors for the entities found in it. It is more effective than a 'bag-of-words' image representation, because the 'imageas-knowledge' vectors encode information about the graph structure. CoAttention uses the words of the query to compute weighted combinations of the entity vectors, in effect a vector within the span of the image entities. Two such iden-

show abstract

“…The first two authors contribute equally Recent works show that KGEs are inclined to manifest bias, and propose methods for debiasing them (Fisher et al, 2020a;Arduini et al, 2020;Bose and Hamilton, 2019). However, these works implicitly assume that the relations to be debiased are chosen by the practitioner without quantification (e.g.…”

Section: Introductionmentioning

confidence: 99%

Towards Automatic Bias Detection in Knowledge Graphs

Keidar¹,

Zhong²,

Zhang³

et al. 2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

With the recent surge in social applications relying on knowledge graphs, the need for techniques to ensure fairness in KG based methods is becoming increasingly evident. Previous works have demonstrated that KGs are prone to various social biases, and have proposed multiple methods for debiasing them. However, in such studies, the focus has been on debiasing techniques, while the relations to be debiased are specified manually by the user. As manual specification is itself susceptible to human cognitive bias, there is a need for a system capable of quantifying and exposing biases, that can support more informed decisions on what to debias. To address this gap in the literature, we describe a framework for identifying biases present in knowledge graph embeddings, based on numerical bias metrics. We illustrate the framework with three different bias measures on the task of profession prediction, and it can be flexibly extended to further bias definitions and applications. The relations flagged as biased can then be handed to decision makers for judgement upon subsequent debiasing.

show abstract

Debiasing knowledge graph embeddings

Cited by 39 publications

References 16 publications

FMP: Toward Fair Graph Message Passing against Topology Bias

FMP: Toward Fair Graph Message Passing against Topology Bias

Seeing is Knowing! Fact-based Visual Question Answering using Knowledge Graph Embeddings

Towards Automatic Bias Detection in Knowledge Graphs

Contact Info

Product

Resources

About