Unsupervised Abstract Reasoning for Raven's Problem Matrices

• URL: http://arxiv.org/abs/2109.10011v1
• Date: Tue, 21 Sep 2021 07:44:58 GMT
• Title: Unsupervised Abstract Reasoning for Raven's Problem Matrices
• Authors: Tao Zhuo, Qiang Huang, and Mohan Kankanhalli
• Abstract summary: Raven's Progressive Matrices ( RPM) is highly correlated with human intelligence. We propose the first unsupervised learning method for solving RPM problems. Our method even outperforms some of the supervised approaches.
• Score: 9.278113063631643
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Raven's Progressive Matrices (RPM) is highly correlated with human intelligence, and it has been widely used to measure the abstract reasoning ability of humans. In this paper, to study the abstract reasoning capability of deep neural networks, we propose the first unsupervised learning method for solving RPM problems. Since the ground truth labels are not allowed, we design a pseudo target based on the prior constraints of the RPM formulation to approximate the ground truth label, which effectively converts the unsupervised learning strategy into a supervised one. However, the correct answer is wrongly labelled by the pseudo target, and thus the noisy contrast will lead to inaccurate model training. To alleviate this issue, we propose to improve the model performance with negative answers. Moreover, we develop a decentralization method to adapt the feature representation to different RPM problems. Extensive experiments on three datasets demonstrate that our method even outperforms some of the supervised approaches. Our code is available at https://github.com/visiontao/ncd.

Related papers

• Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method [115.29382166356478]
  We introduce the adversarial retrieval attack (AREA) task. It is meant to trick DR models into retrieving a target document that is outside the initial set of candidate documents retrieved by the DR model. We find that the promising results that have previously been reported on attacking NRMs, do not generalize to DR models. We propose to formalize attacks on DR models as a contrastive learning problem in a multi-view representation space.
  arXiv  Detail & Related papers  (2023-08-19T00:24:59Z)
• Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability [6.33280703577189]
  We show that end-to-end neural networks embodied with inductive bias, intentionally design or serendipitously match, can solve RPM problems. Our work also reveals that multi-viewpoint with multi-evaluation is a key learning strategy for successful reasoning. We hope that these results will serve as inspections of AI's ability beyond perception and toward abstract reasoning.
  arXiv  Detail & Related papers  (2022-10-26T17:15:44Z)
• Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels [112.63440666617494]
  Reinforcement learning algorithms can succeed but require large amounts of interactions between the agent and the environment. We propose a new method to solve it, using unsupervised model-based RL, for pre-training the agent. We show robust performance on the Real-Word RL benchmark, hinting at resiliency to environment perturbations during adaptation.
  arXiv  Detail & Related papers  (2022-09-24T14:22:29Z)
• Effective Abstract Reasoning with Dual-Contrast Network [10.675709291797535]
  We aim to solve Raven's Progressive Matrices ( RPM) puzzles with neural networks. We design a simple yet effective Dual-Contrast Network (DCNet) to exploit the inherent structure of RPM puzzles. Experimental results on the RAVEN and PGM datasets show that DCNet outperforms the state-of-the-art methods by a large margin of 5.77%.
  arXiv  Detail & Related papers  (2022-05-27T02:26:52Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Robust Predictable Control [149.71263296079388]
  We show that our method achieves much tighter compression than prior methods, achieving up to 5x higher reward than a standard information bottleneck. We also demonstrate that our method learns policies that are more robust and generalize better to new tasks.
  arXiv  Detail & Related papers  (2021-09-07T17:29:34Z)
• Regressive Domain Adaptation for Unsupervised Keypoint Detection [67.2950306888855]
  Domain adaptation (DA) aims at transferring knowledge from a labeled source domain to an unlabeled target domain. We present a method of regressive domain adaptation (RegDA) for unsupervised keypoint detection. Our method brings large improvement by 8% to 11% in terms of PCK on different datasets.
  arXiv  Detail & Related papers  (2021-03-10T16:45:22Z)
• Multi-Label Contrastive Learning for Abstract Visual Reasoning [0.0]
  State-of-the-art systems solving Raven's Progressive Matrices rely on massive pattern-based training and exploiting biases in the dataset. Humans concentrate on identification of the rules / concepts underlying the RPM (or generally a visual reasoning task) to be solved. We propose a new sparse rule encoding scheme for RPMs which, besides the new training algorithm, is the key factor contributing to the state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-12-03T14:18:15Z)
• Stratified Rule-Aware Network for Abstract Visual Reasoning [46.015682319351676]
  Raven's Progressive Matrices (RPM) test is typically used to examine the capability of abstract reasoning. Recent studies, taking advantage of Convolutional Neural Networks (CNNs), have achieved encouraging progress to accomplish the RPM test. We propose a Stratified Rule-Aware Network (SRAN) to generate the rule embeddings for two input sequences.
  arXiv  Detail & Related papers  (2020-02-17T08:44:05Z)
• Solving Raven's Progressive Matrices with Neural Networks [10.675709291797535]
  Raven's Progressive Matrices (RPM) have been widely used for Intelligence Quotient (IQ) test of humans. In this paper, we aim to solve RPM with neural networks in both supervised and unsupervised manners.
  arXiv  Detail & Related papers  (2020-02-05T05:18:02Z)

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.