Multitask Kernel-based Learning with Logic Constraints
- URL: http://arxiv.org/abs/2402.10617v1
- Date: Fri, 16 Feb 2024 12:11:34 GMT
- Title: Multitask Kernel-based Learning with Logic Constraints
- Authors: Michelangelo Diligenti, Marco Gori, Marco Maggini, Leonardo Rigutini
- Abstract summary: This paper presents a framework to integrate prior knowledge in the form of logic constraints among a set of task functions into kernel machines.
We consider a multi-task learning scheme, where multiple unary predicates on the feature space are to be learned by kernel machines.
A general approach is presented to convert the logic clauses into a continuous implementation, that processes the outputs computed by the kernel-based predicates.
- Score: 13.70920563542248
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper presents a general framework to integrate prior knowledge in the
form of logic constraints among a set of task functions into kernel machines.
The logic propositions provide a partial representation of the environment, in
which the learner operates, that is exploited by the learning algorithm
together with the information available in the supervised examples. In
particular, we consider a multi-task learning scheme, where multiple unary
predicates on the feature space are to be learned by kernel machines and a
higher level abstract representation consists of logic clauses on these
predicates, known to hold for any input. A general approach is presented to
convert the logic clauses into a continuous implementation, that processes the
outputs computed by the kernel-based predicates. The learning task is
formulated as a primal optimization problem of a loss function that combines a
term measuring the fitting of the supervised examples, a regularization term,
and a penalty term that enforces the constraints on both supervised and
unsupervised examples. The proposed semi-supervised learning framework is
particularly suited for learning in high dimensionality feature spaces, where
the supervised training examples tend to be sparse and generalization
difficult. Unlike for standard kernel machines, the cost function to optimize
is not generally guaranteed to be convex. However, the experimental results
show that it is still possible to find good solutions using a two stage
learning schema, in which first the supervised examples are learned until
convergence and then the logic constraints are forced. Some promising
experimental results on artificial multi-task learning tasks are reported,
showing how the classification accuracy can be effectively improved by
exploiting the a priori rules and the unsupervised examples.
Related papers
- STAND: Data-Efficient and Self-Aware Precondition Induction for Interactive Task Learning [0.0]
STAND is a data-efficient and computationally efficient machine learning approach.
It produces better classification accuracy than popular approaches like XGBoost.
It produces a measure called instance certainty that can predict increases in holdout set performance.
arXiv Detail & Related papers (2024-09-11T22:49:38Z) - Multitask Kernel-based Learning with First-Order Logic Constraints [13.70920563542248]
We consider a multi-task learning scheme where multiple predicates defined on a set of objects are to be jointly learned from examples.
A general approach is presented to convert the FOL clauses into a continuous implementation that can deal with the outputs computed by the kernel-based predicates.
arXiv Detail & Related papers (2023-11-06T18:44:55Z) - Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning [83.41487567765871]
Skipper is a model-based reinforcement learning framework.
It automatically generalizes the task given into smaller, more manageable subtasks.
It enables sparse decision-making and focused abstractions on the relevant parts of the environment.
arXiv Detail & Related papers (2023-09-30T02:25:18Z) - Interpretable Anomaly Detection via Discrete Optimization [1.7150329136228712]
We propose a framework for learning inherently interpretable anomaly detectors from sequential data.
We show that this problem is computationally hard and develop two learning algorithms based on constraint optimization.
Using a prototype implementation, we demonstrate that our approach shows promising results in terms of accuracy and F1 score.
arXiv Detail & Related papers (2023-03-24T16:19:15Z) - Stabilizing Q-learning with Linear Architectures for Provably Efficient
Learning [53.17258888552998]
This work proposes an exploration variant of the basic $Q$-learning protocol with linear function approximation.
We show that the performance of the algorithm degrades very gracefully under a novel and more permissive notion of approximation error.
arXiv Detail & Related papers (2022-06-01T23:26:51Z) - Exploring Viable Algorithmic Options for Learning from Demonstration
(LfD): A Parameterized Complexity Approach [0.0]
In this paper, we show how such a systematic exploration of algorithmic options can be done using parameterized complexity analysis.
We show that none of our problems can be solved efficiently either in general or relative to a number of (often simultaneous) restrictions on environments, demonstrations, and policies.
arXiv Detail & Related papers (2022-05-10T15:54:06Z) - Fine-grained Generalization Analysis of Vector-valued Learning [28.722350261462463]
We start the generalization analysis of regularized vector-valued learning algorithms by presenting bounds with a mild dependency on the output dimension and a fast rate on the sample size.
To understand the interaction between optimization and learning, we further use our results to derive the first bounds for descent with vector-valued functions.
As a byproduct, we derive a Rademacher complexity bound for loss function classes defined in terms of a general strongly convex function.
arXiv Detail & Related papers (2021-04-29T07:57:34Z) - Multi-Agent Reinforcement Learning with Temporal Logic Specifications [65.79056365594654]
We study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment.
We develop the first multi-agent reinforcement learning technique for temporal logic specifications.
We provide correctness and convergence guarantees for our main algorithm.
arXiv Detail & Related papers (2021-02-01T01:13:03Z) - An Integer Linear Programming Framework for Mining Constraints from Data [81.60135973848125]
We present a general framework for mining constraints from data.
In particular, we consider the inference in structured output prediction as an integer linear programming (ILP) problem.
We show that our approach can learn to solve 9x9 Sudoku puzzles and minimal spanning tree problems from examples without providing the underlying rules.
arXiv Detail & Related papers (2020-06-18T20:09:53Z) - An Information Bottleneck Approach for Controlling Conciseness in
Rationale Extraction [84.49035467829819]
We show that it is possible to better manage this trade-off by optimizing a bound on the Information Bottleneck (IB) objective.
Our fully unsupervised approach jointly learns an explainer that predicts sparse binary masks over sentences, and an end-task predictor that considers only the extracted rationale.
arXiv Detail & Related papers (2020-05-01T23:26:41Z) - Learning What Makes a Difference from Counterfactual Examples and
Gradient Supervision [57.14468881854616]
We propose an auxiliary training objective that improves the generalization capabilities of neural networks.
We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task.
Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
arXiv Detail & Related papers (2020-04-20T02:47:49Z)
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.