Aligning Knowledge Graphs Provided by Humans and Generated from Neural Networks in Specific Tasks
- URL: http://arxiv.org/abs/2404.16884v1
- Date: Tue, 23 Apr 2024 20:33:17 GMT
- Title: Aligning Knowledge Graphs Provided by Humans and Generated from Neural Networks in Specific Tasks
- Authors: Tangrui Li, Jun Zhou,
- Abstract summary: This paper develops an innovative method that enables neural networks to generate and utilize knowledge graphs.
Our approach eschews traditional dependencies on or word embedding models, mining concepts from neural networks and directly aligning them with human knowledge.
Experiments show that our method consistently captures network-generated concepts that align closely with human knowledge and can even uncover new, useful concepts not previously identified by humans.
- Score: 5.791414814676125
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper develops an innovative method that enables neural networks to generate and utilize knowledge graphs, which describe their concept-level knowledge and optimize network parameters through alignment with human-provided knowledge. This research addresses a gap where traditionally, network-generated knowledge has been limited to applications in downstream symbolic analysis or enhancing network transparency. By integrating a novel autoencoder design with the Vector Symbolic Architecture (VSA), we have introduced auxiliary tasks that support end-to-end training. Our approach eschews traditional dependencies on ontologies or word embedding models, mining concepts from neural networks and directly aligning them with human knowledge. Experiments show that our method consistently captures network-generated concepts that align closely with human knowledge and can even uncover new, useful concepts not previously identified by humans. This plug-and-play strategy not only enhances the interpretability of neural networks but also facilitates the integration of symbolic logical reasoning within these systems.
Related papers
- Discovering Chunks in Neural Embeddings for Interpretability [53.80157905839065]
We propose leveraging the principle of chunking to interpret artificial neural population activities.
We first demonstrate this concept in recurrent neural networks (RNNs) trained on artificial sequences with imposed regularities.
We identify similar recurring embedding states corresponding to concepts in the input, with perturbations to these states activating or inhibiting the associated concepts.
arXiv Detail & Related papers (2025-02-03T20:30:46Z) - Concept Learning in the Wild: Towards Algorithmic Understanding of Neural Networks [2.102973349909511]
We study concept learning for an existing graph neural networks (GNN) model trained to solve Boolean satisfiability (SAT)
Our analysis reveals that the model learns key concepts matching those guiding human-designed SATs, particularly the notion of'support'
We use the discovered concepts to "reverse-engineer" the black-box GNN and rewrite it as a white-box textbook algorithm.
arXiv Detail & Related papers (2024-12-15T14:37:56Z) - Neural-Symbolic Reasoning over Knowledge Graphs: A Survey from a Query Perspective [55.79507207292647]
Knowledge graph reasoning is pivotal in various domains such as data mining, artificial intelligence, the Web, and social sciences.
The rise of Neural AI marks a significant advancement, merging the robustness of deep learning with the precision of symbolic reasoning.
The advent of large language models (LLMs) has opened new frontiers in knowledge graph reasoning.
arXiv Detail & Related papers (2024-11-30T18:54:08Z) - Identifying Sub-networks in Neural Networks via Functionally Similar Representations [41.028797971427124]
We take a step toward automating the understanding of the network by investigating the existence of distinct sub-networks.
Specifically, we explore a novel automated and task-agnostic approach based on the notion of functionally similar representations within neural networks.
We show the proposed approach offers meaningful insights into the behavior of neural networks with minimal human and computational cost.
arXiv Detail & Related papers (2024-10-21T20:19:00Z) - A short Survey: Exploring knowledge graph-based neural-symbolic system from application perspective [0.0]
achieving human-like reasoning and interpretability in AI systems remains a substantial challenge.
The Neural-Symbolic paradigm, which integrates neural networks with symbolic systems, presents a promising pathway toward more interpretable AI.
This paper explores recent advancements in neural-symbolic integration based on Knowledge Graphs.
arXiv Detail & Related papers (2024-05-06T14:40:50Z) - From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks [15.837316393474403]
Concepts can act as a natural link between learning and reasoning.
Knowledge can not only be extracted from neural networks but concept knowledge can also be inserted into neural network architectures.
arXiv Detail & Related papers (2023-10-18T11:08:02Z) - Synergistic information supports modality integration and flexible
learning in neural networks solving multiple tasks [107.8565143456161]
We investigate the information processing strategies adopted by simple artificial neural networks performing a variety of cognitive tasks.
Results show that synergy increases as neural networks learn multiple diverse tasks.
randomly turning off neurons during training through dropout increases network redundancy, corresponding to an increase in robustness.
arXiv Detail & Related papers (2022-10-06T15:36:27Z) - Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces [20.260546238369205]
We propose a framework that combines the pattern recognition abilities of neural networks with symbolic reasoning and background knowledge.
We take inspiration from the 'neural algorithmic reasoning' approach [DeepMind 2020] and use problem-specific background knowledge.
We test this on visual analogy problems in RAVENs Progressive Matrices, and achieve accuracy competitive with human performance.
arXiv Detail & Related papers (2022-09-19T04:03:20Z) - Neuro-Symbolic Learning of Answer Set Programs from Raw Data [54.56905063752427]
Neuro-Symbolic AI aims to combine interpretability of symbolic techniques with the ability of deep learning to learn from raw data.
We introduce Neuro-Symbolic Inductive Learner (NSIL), an approach that trains a general neural network to extract latent concepts from raw data.
NSIL learns expressive knowledge, solves computationally complex problems, and achieves state-of-the-art performance in terms of accuracy and data efficiency.
arXiv Detail & Related papers (2022-05-25T12:41:59Z) - Data-driven emergence of convolutional structure in neural networks [83.4920717252233]
We show how fully-connected neural networks solving a discrimination task can learn a convolutional structure directly from their inputs.
By carefully designing data models, we show that the emergence of this pattern is triggered by the non-Gaussian, higher-order local structure of the inputs.
arXiv Detail & Related papers (2022-02-01T17:11:13Z) - Learning Connectivity of Neural Networks from a Topological Perspective [80.35103711638548]
We propose a topological perspective to represent a network into a complete graph for analysis.
By assigning learnable parameters to the edges which reflect the magnitude of connections, the learning process can be performed in a differentiable manner.
This learning process is compatible with existing networks and owns adaptability to larger search spaces and different tasks.
arXiv Detail & Related papers (2020-08-19T04:53:31Z)
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.