SRN improves set representations for relational reasoning.
problem Set permutational invariance limitations in existing approaches.
method Proposed a Set Refiner Network (SRN) to respect set invariance.
result Substantial gains in prediction performance and robustness on relational reasoning tasks.
ResMixNet models learn invariant relational reasoning tasks with fewer parameters.
problem Learning invariant relational reasoning tasks in images with random transformations.
method Introduced Residual Mixture Network (ResMixNet) with a mixture-of-experts architecture.
result ResMixNet models achieve less than 2% test error on MNIST Parity task and less than 1% on colorized Pentomino task.
End-to-end multi-object tracking learns object interactions.
problem Object tracking ignores interactions between objects.
method End-to-end relational reasoning model MOHART.
result Relational reasoning improves tracking and prediction.
Paper proves efficiency of MARL with transformers, addressing agent complexity.
problem Theoretical understanding of MARL with many agents and limited relational reasoning.
method Set Transformer for relational reasoning, model-free and model-based MARL algorithms.
result Provable efficiency of MARL algorithms, suboptimality gaps independent of number of agents.
Dilated DenseNets excel at relational reasoning without additional modules.
problem Deep neural networks struggle with relational reasoning.
method Dilated DenseNet architecture incorporating dilated convolutions.
result Dilated DenseNets surpass relational reasoning on Sort-of-CLEVR without additional modules.
SARN improves relational reasoning with less computation.
problem Efficiently perform relational reasoning with reduced computation.
method Introduces SARN, a sequential attention relational network.
result SARN achieves high accuracy on relational questions.
Enhances relational reasoning with multi-layer architecture.
problem Limited relational reasoning with shallow architectures.
method Multi-layer relation network architecture.
result Solved all 20 tasks in bAbI 20 QA dataset.
New invariant shows no homotopy 4-sphere difference.
problem Determining homotopy 4-spheres using ECH and SWF.
method Embedded contact homology (ECH) and Seiberg-Witten theory (SWF).
result ECH and SWF are ineffective for distinguishing homotopy 4-spheres.
Abstractor enhances Transformers for relational reasoning, improving sample efficiency and performance.
problem Improving sample efficiency and performance in relational tasks.
method Introduces Abstractor module with relational cross-attention to enable explicit relational reasoning.
result Dramatic improvements in sample efficiency and performance on various relational tasks.
Cognitive KR model learns new facts from few examples.
problem Inferring new facts from small KG datasets.
method CogKR combines summary and reasoning modules with cognitive science principles.
result Significantly outperforms previous models on one-shot KG reasoning.
ARNe model excels in abstract visual reasoning tasks.
problem Abstract visual reasoning using attention mechanisms.
method Hybrid network architecture combining self-attention and relational reasoning.
result ARNe model surpasses WReN model by 11.28 ppt on PGM datasets.
Consider an asymptotically flat Riemannian manifold (M,g) of dimension n≥3 with nonempty compact boundary. We recall the harmonic conformal class [g]h of the metric, which consists of all conformal rescalings given by a harmonic function raised to an appropriate power. The geometric significance is that eve…
The famous Nash embedding theorem was aimed for in the hope that if Riemannian manifolds could be regarded as Riemannian submanifolds, this would then yield the opportunity to use extrinsic help. However, as late as 1985 (see \cite{G}) this hope had not been materialized. The main reason for this is due to the lack of …
New memory module improves relational reasoning in neural networks.
problem Standard memory architectures struggle with relational reasoning tasks.
method Introduce a new memory module called Relational Memory Core (RMC) using multi-head dot product attention.
result Achieves state-of-the-art results on various datasets, including WikiText-103, Project Gutenberg, and GigaWord.
Improved neural networks for relational reasoning by projecting high-dimensional data to low-dimensional manifolds.
problem Out-of-distribution generalization in complex relational reasoning tasks.
method Neuroscience-inspired inductive-biased module projecting high-dimensional object representations to low-dimensional manifolds.
result Significantly better out-of-distribution generalization performance on relational reasoning tasks.
New task AQA tackles acoustic reasoning from sound scenes.
problem Promote research in acoustic reasoning.
method Generate acoustic scenes from elementary sounds and formulate questions.
result Preliminary results with models FiLM and MAC show promise.
Continuing the work started in Part I and II of this series (see q-alg/9706004 and math.QA/9801049), we prove the relationship between the Aarhus integral and the invariant Ω (henceforth called LMO) defined by T.Q.T. Le, J. Murakami and T. Ohtsuki in q-alg/9512002. The basic reason for the relationship is that both c…
Self-supervised method improves representation learning for better accuracy.
problem Improving representation learning without manual annotation.
method Proposes a novel self-supervised formulation of relational reasoning.
result Self-supervised relational reasoning outperforms state-of-the-art models by 14% in accuracy.
DAM with MRL improves relational reasoning in MANNs.
problem Limited performance of associative memory networks on complex relational reasoning tasks.
method Distributed Associative Memory architecture with Memory Refreshing Loss.
result Enhanced relation reasoning performance of MANNs on long temporal sequence data.
Enhances RL with relational reasoning, improving efficiency and interpretability.
problem Challenges in deep reinforcement learning, especially sample complexity and generalization.
method Structured perception and relational reasoning using self-attention.
result Agent finds interpretable solutions that generalize better and perform better than baselines.
GraIL predicts relations by reasoning over subgraphs, outperforming embeddings.
problem Relation prediction in knowledge graphs using latent representations is limited.
method Graph neural network with inductive bias to learn entity-independent relational semantics.
result GraIL outperforms existing rule-induction baselines in the inductive setting.
Deep neural networks solve Raven's Progressive Matrices with high accuracy.
problem Testing relational reasoning in machine learning systems.
method Combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding.
result Deep neural networks achieve 98.0 percent accuracy, significantly improving over previous methods.
The Plebanski formulation of complex general relativity is given in terms of variables valued in the complexification of the so(3) Lie algebra. Therefore, it is genuinely a gauge theory that is also diffeomorphism-invariant. For this reason, the way that the Levi-Civita connection emerges from this formulation is not…
Entity-GCN model answers multi-document questions by reasoning across documents.
problem Answering questions based on multiple documents and cross-document relations.
method Graph Convolutional Networks (GCNs) applied to a graph of mentions and their relations.
result Achieves state-of-the-art results on WikiHop dataset.
Graph neural networks improve combinatorial optimization by leveraging inductive bias.
problem Combinatorial optimization problems often arise from related data distributions.
method Using graph neural networks to enhance or solve combinatorial tasks.
result Graph neural networks effectively encode combinatorial and relational input.
TRR detects stock portfolio crashes by simulating human reasoning.
problem Detecting stock portfolio crashes with limited historical data.
method Temporal Relational Reasoning (TRR) framework.
result TRR outperforms state-of-the-art techniques in detecting stock portfolio crashes.
We consider two approaches to isotopy invariants of oriented links: one from ribbon categories and the other from generalized Yang-Baxter operators with appropriate enhancements. The generalized Yang-Baxter operators we consider are obtained from so-called gYBE objects following a procedure of Kitaev and Wang. We show …
ENN neural network learns logical syllogisms using Euler diagrams.
problem Traditional neural networks struggle with logical reasoning, especially syllogisms.
method ENN represents logical relations as Euler diagrams, optimizing syllogism structures with a novel back-propagation algorithm.
result ENN can precisely represent and reason with all 24 syllogism structures.
Constellation learns group-level visual relationships for abstract reasoning.
problem Learning configurational properties of entire groups of objects.
method Introduces Constellation, a network that learns relational abstractions over static visual scenes.
result Offers a basis for abstract relational reasoning and sensory imagination.
SpatialSim benchmarks machine learning in recognizing object spatial configurations.
problem Machine learning in recognizing precise geometrical configurations of groups of objects.
method SpatialSim benchmark with tasks of Identification and Comparison, using Graph Neural Networks (MPGNNs).
result MPGNNs outperform baselines in recognizing spatial configurations, highlighting current limits.
Few-shot visual reasoning model learns analogical relationships from small data.
problem Training deep models on few samples for visual reasoning tasks.
method Meta-analogical contrastive learning to enforce structural similarity between training and test samples.
result Method outperforms state-of-the-art on RAVEN dataset with scarce training data.
A new method learns object hierarchies from images to reason about physical interactions.
problem Learning about the interactions of complex objects and their dynamics.
method Unsupervised learning of object hierarchies from raw visual images.
result Improves over a strong baseline at modeling synthetic and real-world videos.
In his study of Ricci flow, Perelman introduced a smooth-manifold invariant called lambda-bar. We show here that, for completely elementary reasons, this invariant simply equals the Yamabe invariant, alias the sigma constant, whenever the latter is non-positive. On the other hand, the Perelman invariant just equals + i…
Improved RL for knowledge graph reasoning with entity types.
problem Challenges in path-based relational reasoning over knowledge graphs.
method Type-enhanced RL agent using GNN for neighborhood information.
result Outperforms state-of-the-art RL methods and discovers novel paths.
NLM combines neural networks and logic programming for complex reasoning.
problem Complex reasoning tasks involving logic and properties.
method Neural-symbolic architecture combining neural networks and logic programming.
result NLM achieves perfect generalization on various tasks.
Bayesian framework integrates spectral deconvolution with expert reasoning for robust peak estimation.
problem Challenges in extracting meaningful peaks from noisy or complex spectra.
method Bayesian spectral deconvolution coupled with a physical-property regression layer.
result Recovery of weak peaks in poly(lactic acid) IR spectra related to degradation rates.
Improved generalization in abstract reasoning tasks using disentangled latent representations.
problem Improving generalization in unsupervised representation learning for abstract reasoning.
method Used disentangled VAEs to learn latent representations from relational reasoning problems.
result Disentangled latent representations outperform supervised learning in generalization.
Neural-symbolic model improves link prediction in knowledge graphs.
problem Effective relational learning and reasoning for AI systems.
method Neural-symbolic graph neural network that learns over all paths in knowledge graphs.
result Neural-symbolic model outperforms path-based approaches in link prediction.
Paper proposes Unification Networks to learn invariants from examples.
problem Learning to recognize common underlying principles across examples.
method End-to-end differentiable neural network approach with soft unification.
result Learning invariants improves performance on various datasets.
Relational Structural Causal Models enable causal reasoning about unseen object combinations.
problem Developing a model that can reason about causal and combinatorial aspects of unseen object combinations.
method Relational Structural Causal Models extend structural causal models to include relational variables and define identification criteria.
result Proposed relational neural causal models outperform non-relational baselines on simulated traffic scenes.
A neural network learns relational representations from raw data.
problem Learning reusable representations from raw pixel data.
method Explicitly relational neural network architecture trained on visual relational tasks.
result The architecture outperforms baselines on unseen tasks.
Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Stand…
Improved few-shot visual reasoning with image preprocessing.
problem Few-shot classifiers struggle with abstract visual reasoning tasks.
method Spectral feature removal to emphasize unique image parts.
result Combining spectral preprocessing with Relational Networks improves accuracy nearly 40%.
Sparse hypergraph neural networks improve reasoning in large knowledge graphs.
problem Reasoning about relationships in large, real-world domains using sparse and local inferences.
method Sparse and local hypergraph neural networks (SpaLoc) exploiting relational inferences that are usually local and sparse.
result State-of-the-art performance on real-world knowledge graph reasoning benchmarks.
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
problem Hallucinations and laziness in LLM reasoning tasks.
method Expert Iteration explores reasoning trajectories, guiding incorrect paths back on track and promoting appropriate 'I don't know' responses.
result Auto-CEI achieves superior alignment in logical reasoning, mathematics, and planning tasks.
Improves neural relational inference for dynamic multi-agent trajectories.
problem Limited accuracy of NRI in short output sequences for relational inference in multi-agent trajectories.
method Proposes DYnamic multi-AgentRelational Inference (DYARI) model to handle changing interactions over time.
result DYARI model outperforms NRI in dynamic relational inference tasks.
While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks. We hypothesize that what these systems lack is a "relational inductive bias": a capacity for reasoning about inter-object relations…
Paper improves text-to-SQL translation by encoding schema relations with self-attention.
problem Improving text-to-SQL translation accuracy across diverse databases.
method Uses relation-aware self-attention to encode schema information.
result Significant gains on Spider dataset (42.94% exact match accuracy).