Adversarial Learning for Debiasing Knowledge Graph Embeddings
- URL: http://arxiv.org/abs/2006.16309v2
- Date: Thu, 18 Feb 2021 02:16:59 GMT
- Title: Adversarial Learning for Debiasing Knowledge Graph Embeddings
- Authors: Mario Arduini, Lorenzo Noci, Federico Pirovano, Ce Zhang, Yash Raj
Shrestha, Bibek Paudel
- Abstract summary: Social and cultural biases can have detrimental consequences on different population and minority groups.
This paper aims at identifying and mitigating such biases in Knowledge Graph (KG) embeddings.
We introduce a novel framework to filter out the sensitive attribute information from the KG embeddings, which we call FAN (Filtering Adversarial Network)
- Score: 9.53284633479507
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Knowledge Graphs (KG) are gaining increasing attention in both academia and
industry. Despite their diverse benefits, recent research have identified
social and cultural biases embedded in the representations learned from KGs.
Such biases can have detrimental consequences on different population and
minority groups as applications of KG begin to intersect and interact with
social spheres. This paper aims at identifying and mitigating such biases in
Knowledge Graph (KG) embeddings. As a first step, we explore popularity bias --
the relationship between node popularity and link prediction accuracy. In case
of node2vec graph embeddings, we find that prediction accuracy of the embedding
is negatively correlated with the degree of the node. However, in case of
knowledge-graph embeddings (KGE), we observe an opposite trend. As a second
step, we explore gender bias in KGE, and a careful examination of popular KGE
algorithms suggest that sensitive attribute like the gender of a person can be
predicted from the embedding. This implies that such biases in popular KGs is
captured by the structural properties of the embedding. As a preliminary
solution to debiasing KGs, we introduce a novel framework to filter out the
sensitive attribute information from the KG embeddings, which we call FAN
(Filtering Adversarial Network). We also suggest the applicability of FAN for
debiasing other network embeddings which could be explored in future work.
Related papers
- Graph Out-of-Distribution Generalization via Causal Intervention [69.70137479660113]
We introduce a conceptually simple yet principled approach for training robust graph neural networks (GNNs) under node-level distribution shifts.
Our method resorts to a new learning objective derived from causal inference that coordinates an environment estimator and a mixture-of-expert GNN predictor.
Our model can effectively enhance generalization with various types of distribution shifts and yield up to 27.4% accuracy improvement over state-of-the-arts on graph OOD generalization benchmarks.
arXiv Detail & Related papers (2024-02-18T07:49:22Z) - EntailE: Introducing Textual Entailment in Commonsense Knowledge Graph
Completion [54.12709176438264]
Commonsense knowledge graphs (CSKGs) utilize free-form text to represent named entities, short phrases, and events as their nodes.
Current methods leverage semantic similarities to increase the graph density, but the semantic plausibility of the nodes and their relations are under-explored.
We propose to adopt textual entailment to find implicit entailment relations between CSKG nodes, to effectively densify the subgraph connecting nodes within the same conceptual class.
arXiv Detail & Related papers (2024-02-15T02:27:23Z) - CausE: Towards Causal Knowledge Graph Embedding [13.016173217017597]
Knowledge graph embedding (KGE) focuses on representing the entities and relations of a knowledge graph (KG) into the continuous vector spaces.
We build the new paradigm of KGE in the context of causality and embedding disentanglement.
We propose a Causality-enhanced knowledge graph Embedding (CausE) framework.
arXiv Detail & Related papers (2023-07-21T14:25:39Z) - Diversity matters: Robustness of bias measurements in Wikidata [4.950095974653716]
We reveal data biases that surface in Wikidata for thirteen different demographics selected from seven continents.
We conduct our extensive experiments on a large number of occupations sampled from the thirteen demographics with respect to the sensitive attribute, i.e., gender.
We show that the choice of the state-of-the-art KG embedding algorithm has a strong impact on the ranking of biased occupations irrespective of gender.
arXiv Detail & Related papers (2023-02-27T18:38:10Z) - Toward Degree Bias in Embedding-Based Knowledge Graph Completion [37.270356897629675]
Degree bias can affect graph algorithms by learning poor representations for lower-degree nodes.
In this paper, we validate the existence of degree bias in embedding-based knowledge graphs and identify the key factor to degree bias.
We then introduce a novel data augmentation method, KG-Mixup, to generate synthetic triples to mitigate such bias.
arXiv Detail & Related papers (2023-02-10T04:14:45Z) - Mitigating Relational Bias on Knowledge Graphs [51.346018842327865]
We propose Fair-KGNN, a framework that simultaneously alleviates multi-hop bias and preserves the proximity information of entity-to-relation in knowledge graphs.
We develop two instances of Fair-KGNN incorporating with two state-of-the-art KGNN models, RGCN and CompGCN, to mitigate gender-occupation and nationality-salary bias.
arXiv Detail & Related papers (2022-11-26T05:55:34Z) - Explainable Sparse Knowledge Graph Completion via High-order Graph
Reasoning Network [111.67744771462873]
This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs)
It combines high-order reasoning into a graph convolutional network, namely HoGRN.
It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
arXiv Detail & Related papers (2022-07-14T10:16:56Z) - Towards Automatic Bias Detection in Knowledge Graphs [5.402498799294428]
We describe a framework for identifying biases in knowledge graph embeddings, based on numerical bias metrics.
We illustrate the framework with three different bias measures on the task of profession prediction.
The relations flagged as biased can then be handed to decision makers for judgement upon subsequent debiasing.
arXiv Detail & Related papers (2021-09-19T03:58:25Z) - Learning Intents behind Interactions with Knowledge Graph for
Recommendation [93.08709357435991]
Knowledge graph (KG) plays an increasingly important role in recommender systems.
Existing GNN-based models fail to identify user-item relation at a fine-grained level of intents.
We propose a new model, Knowledge Graph-based Intent Network (KGIN)
arXiv Detail & Related papers (2021-02-14T03:21:36Z) - RelWalk A Latent Variable Model Approach to Knowledge Graph Embedding [50.010601631982425]
This paper extends the random walk model (Arora et al., 2016a) of word embeddings to Knowledge Graph Embeddings (KGEs)
We derive a scoring function that evaluates the strength of a relation R between two entities h (head) and t (tail)
We propose a learning objective motivated by the theoretical analysis to learn KGEs from a given knowledge graph.
arXiv Detail & Related papers (2021-01-25T13:31:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.