Pairwise Relations Discriminator for Unsupervised Raven's Progressive Matrices

• URL: http://arxiv.org/abs/2011.01306v2
• Date: Thu, 5 Aug 2021 09:11:31 GMT
• Title: Pairwise Relations Discriminator for Unsupervised Raven's Progressive Matrices
• Authors: Nicholas Quek Wei Kiat, Duo Wang, Mateja Jamnik
• Abstract summary: We introduce a pairwise relations discriminator (PRD) to develop unsupervised models with sufficient reasoning abilities to tackle an Raven's Progressive Matrices problem. PRD reframes the RPM problem into a relation comparison task, which we can solve without requiring the labelling of the RPM problem. Our approach, the PRD, establishes a new state-of-the-art unsupervised learning benchmark with an accuracy of 55.9% on the I-RAVEN.
• Score: 7.769102711230249
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ability to hypothesise, develop abstract concepts based on concrete observations and apply these hypotheses to justify future actions has been paramount in human development. An existing line of research in outfitting intelligent machines with abstract reasoning capabilities revolves around the Raven's Progressive Matrices (RPM). There have been many breakthroughs in supervised approaches to solving RPM in recent years. However, this process requires external assistance, and thus it cannot be claimed that machines have achieved reasoning ability comparable to humans. Namely, humans can solve RPM problems without supervision or prior experience once the RPM rule that relations can only exist row/column-wise is properly introduced. In this paper, we introduce a pairwise relations discriminator (PRD), a technique to develop unsupervised models with sufficient reasoning abilities to tackle an RPM problem. PRD reframes the RPM problem into a relation comparison task, which we can solve without requiring the labelling of the RPM problem. We can identify the optimal candidate by adapting the application of PRD to the RPM problem. Our approach, the PRD, establishes a new state-of-the-art unsupervised learning benchmark with an accuracy of 55.9% on the I-RAVEN, presenting a significant improvement and a step forward in equipping machines with abstract reasoning.

Related papers

• Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection [52.107043437362556]
  Raven's Progressive Matrix (RPM) is widely used to probe abstract visual reasoning in machine intelligence. Participators of RPM tests can show powerful reasoning ability by inferring and combining attribute-changing rules. We propose a deep latent variable model for answer generation problems through Rule AbstractIon and SElection.
  arXiv  Detail & Related papers  (2024-01-18T13:28:44Z)
• Negotiated Reasoning: On Provably Addressing Relative Over-Generalization [49.5896371203566]
  Over-generalization is a thorny issue in cognitive science, where people may become overly cautious due to past experiences. Agents in multi-agent reinforcement learning (MARL) also have been found to suffer relative over-generalization (RO) as people do and stuck to sub-optimal cooperation. Recent methods have shown that assigning reasoning ability to agents can mitigate RO algorithmically and empirically, but there has been a lack of theoretical understanding of RO.
  arXiv  Detail & Related papers  (2023-06-08T16:57:12Z)
• Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introduction [3.686658694960549]
  Raven's Progressive Matrices (RPM) tests pose a great challenge for AI systems. There is a long line of computational models for solving RPM, starting from 1960s. This paper provides an all-in-one presentation of computational models for solving RPM.
  arXiv  Detail & Related papers  (2023-02-08T18:09:01Z)
• Hierarchies of Reward Machines [75.55324974788475]
  Reward machines (RMs) are a recent formalism for representing the reward function of a reinforcement learning task through a finite-state machine. We propose a formalism for further abstracting the subtask structure by endowing an RM with the ability to call other RMs.
  arXiv  Detail & Related papers  (2022-05-31T12:39:24Z)
• Reinforcement Learning with a Terminator [80.34572413850186]
  We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds. We use these to construct a provably-efficient algorithm, which accounts for termination, and bound its regret.
  arXiv  Detail & Related papers  (2022-05-30T18:40:28Z)
• Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices [0.0]
  We focus on the most common type of tasks -- the Raven's Progressive Matrices ( RPMs) -- and provide a review of the learning methods and deep neural models applied to solve RPMs. We conclude the paper by demonstrating how real-world problems can benefit from the discoveries of RPM studies.
  arXiv  Detail & Related papers  (2022-01-28T19:24:30Z)
• Modeling Bounded Rationality in Multi-Agent Simulations Using Rationally Inattentive Reinforcement Learning [85.86440477005523]
  We study more human-like RL agents which incorporate an established model of human-irrationality, the Rational Inattention (RI) model. RIRL models the cost of cognitive information processing using mutual information. We show that using RIRL yields a rich spectrum of new equilibrium behaviors that differ from those found under rational assumptions.
  arXiv  Detail & Related papers  (2022-01-18T20:54:00Z)
• One-shot Visual Reasoning on RPMs with an Application to Video Frame Prediction [1.0932251830449902]
  Raven's Progressive Matrices (RPMs) are frequently used in evaluating human's visual reasoning ability. We propose a One-shot Human-Understandable ReaSoner (Os-HURS) to tackle the challenges of real-world visual recognition and subsequent logical reasoning tasks.
  arXiv  Detail & Related papers  (2021-11-24T06:51:38Z)
• Unsupervised Abstract Reasoning for Raven's Problem Matrices [9.278113063631643]
  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.
  arXiv  Detail & Related papers  (2021-09-21T07:44:58Z)
• Self-supervised Representation Learning with Relative Predictive Coding [102.93854542031396]
  Relative Predictive Coding (RPC) is a new contrastive representation learning objective. RPC maintains a good balance among training stability, minibatch size sensitivity, and downstream task performance. We empirically verify the effectiveness of RPC on benchmark vision and speech self-supervised learning tasks.
  arXiv  Detail & Related papers  (2021-03-21T01:04:24Z)
• 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)

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.