Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data

• URL: http://arxiv.org/abs/2301.12321v5
• Date: Mon, 30 Oct 2023 02:36:37 GMT
• Title: Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data
• Authors: Jang-Hyun Kim, Sangdoo Yun, Hyun Oh Song
• Abstract summary: We present scalable algorithms for detecting label errors and outlier data based on the relational graph structure of data. We also introduce a visualization tool that provides contextual information of a data point in the feature-embedded space. Our approach achieves state-of-the-art detection performance on all tasks considered and demonstrates its effectiveness in large-scale real-world datasets.
• Score: 44.64190826937705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diagnosing and cleaning data is a crucial step for building robust machine learning systems. However, identifying problems within large-scale datasets with real-world distributions is challenging due to the presence of complex issues such as label errors, under-representation, and outliers. In this paper, we propose a unified approach for identifying the problematic data by utilizing a largely ignored source of information: a relational structure of data in the feature-embedded space. To this end, we present scalable and effective algorithms for detecting label errors and outlier data based on the relational graph structure of data. We further introduce a visualization tool that provides contextual information of a data point in the feature-embedded space, serving as an effective tool for interactively diagnosing data. We evaluate the label error and outlier/out-of-distribution (OOD) detection performances of our approach on the large-scale image, speech, and language domain tasks, including ImageNet, ESC-50, and SST2. Our approach achieves state-of-the-art detection performance on all tasks considered and demonstrates its effectiveness in debugging large-scale real-world datasets across various domains. We release codes at https://github.com/snu-mllab/Neural-Relation-Graph.

Related papers

• Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach [56.55633052479446]
  Web-scale visual entity recognition presents significant challenges due to the lack of clean, large-scale training data. We propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation. Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks.
  arXiv  Detail & Related papers  (2024-10-31T06:55:24Z)
• ARC: A Generalist Graph Anomaly Detector with In-Context Learning [62.202323209244]
  ARC is a generalist GAD approach that enables a one-for-all'' GAD model to detect anomalies across various graph datasets on-the-fly. equipped with in-context learning, ARC can directly extract dataset-specific patterns from the target dataset. Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance, efficiency, and generalizability of ARC.
  arXiv  Detail & Related papers  (2024-05-27T02:42:33Z)
• GraphGuard: Detecting and Counteracting Training Data Misuse in Graph Neural Networks [69.97213941893351]
  The emergence of Graph Neural Networks (GNNs) in graph data analysis has raised critical concerns about data misuse during model training. Existing methodologies address either data misuse detection or mitigation, and are primarily designed for local GNN models. This paper introduces a pioneering approach called GraphGuard, to tackle these challenges.
  arXiv  Detail & Related papers  (2023-12-13T02:59:37Z)
• ADAMM: Anomaly Detection of Attributed Multi-graphs with Metadata: A Unified Neural Network Approach [39.211176955683285]
  We propose ADAMM, a novel graph neural network model that handles directed multi-graphs. ADAMM fuses metadata and graph-level representation learning through an unsupervised anomaly detection objective.
  arXiv  Detail & Related papers  (2023-11-13T14:19:36Z)
• ALEX: Towards Effective Graph Transfer Learning with Noisy Labels [11.115297917940829]
  We introduce a novel technique termed Balance Alignment and Information-aware Examination (ALEX) to address the problem of graph transfer learning. ALEX first employs singular value decomposition to generate different views with crucial structural semantics, which help provide robust node representations. Building on this foundation, an adversarial domain discriminator is incorporated for the implicit domain alignment of complex multi-modal distributions.
  arXiv  Detail & Related papers  (2023-09-26T04:59:49Z)
• BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection [50.26074811655596]
  We propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE) By swapping the context embeddings between nodes and edges, we enable the mutual detection of node and edge anomalies. BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs.
  arXiv  Detail & Related papers  (2023-07-28T00:44:57Z)
• Learning Strong Graph Neural Networks with Weak Information [64.64996100343602]
  We develop a principled approach to the problem of graph learning with weak information (GLWI) We propose D$2$PT, a dual-channel GNN framework that performs long-range information propagation on the input graph with incomplete structure, but also on a global graph that encodes global semantic similarities.
  arXiv  Detail & Related papers  (2023-05-29T04:51:09Z)
• NetRCA: An Effective Network Fault Cause Localization Algorithm [22.88986905436378]
  Localizing root cause of network faults is crucial to network operation and maintenance. We propose a novel algorithm named NetRCA to deal with this problem. Experiments and analysis are conducted on the real-world dataset from ICASSP 2022 AIOps Challenge.
  arXiv  Detail & Related papers  (2022-02-23T02:03:35Z)
• From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach [26.973056364587766]
  Anomaly detection from graph data is an important data mining task in many applications such as social networks, finance, and e-commerce. We propose a novel framework, graph ANomaly dEtection framework with Multi-scale cONtrastive lEarning (ANEMONE in short) By using a graph neural network as a backbone to encode the information from multiple graph scales (views), we learn better representation for nodes in a graph.
  arXiv  Detail & Related papers  (2022-02-11T09:45:11Z)
• Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection [14.631674952942207]
  We propose a novel method, Self-Supervised Learning for Graph Anomaly Detection (SL-GAD) Our method constructs different contextual subgraphs based on a target node and employs two modules, generative attribute regression and multi-view contrastive learning for anomaly detection. We conduct extensive experiments on six benchmark datasets and the results demonstrate that our method outperforms state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2021-08-23T02:15:21Z)

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.