1,720,971 research outputs found
Knowledge injection of Datalog rules via Neural Network Structuring with KINS
No full textWe propose a novel method to inject symbolic knowledge in form of Datalog formulæ into neural networks (NN), called Knowledge Injection via Network Structuring (KINS). The idea behind our method is to extend NN internal structure with ad-hoc layers built out of the injected symbolic knowledge. KINS does not constrain NN to any specific architecture, neither requires logic formulæ to be ground. Moreover, it is robust w.r.t. both lack of data and imperfect/incomplete knowledge. Experiments are reported, involving multiple datasets and predictor types, to demonstrate how KINS can significantly improve the predictive performance of the neural networks it is applied to
A view to a KILL: Knowledge Injection via Lambda Layer
No full textWe propose KILL (Knowledge Injection via Lambda Layer) as a novel method for the injection of symbolic knowledge into neural networks (NN) allowing data scientists to control what the network should (not) learn. Unlike other similar approaches, our method does not (i) require ground input formulae, (ii) impose any constraint on the NN undergoing injection, (iii) affect the loss function of the NN. Instead, it acts directly at the backpropagation level, by increasing penalty whenever the NN output is violating the injected knowledge. Experiments are reported to demonstrate the potential (and limits) of our approach
On the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors
Full text linkA long-standing ambition in artificial intelligence is to integrate predictors’ inductive features (i.e., learning from examples) with deductive capabilities (i.e., drawing inferences from symbolic knowledge). Many methods in the literature support injection of symbolic knowledge into predictors, generally following the purpose of attaining better (i.e., more effective or efficient w.r.t. predictive performance) predictors. However, to the best of our knowledge, running implementations of these algorithms are currently either proof of concepts or unavailable in most cases. Moreover, a unified, coherent software framework supporting them as well as their interchange, comparison, and exploitation in arbitrary ML workflows is currently missing. Accordingly, in this paper we present the design of PSyKI, a platform providing general-purpose support to symbolic knowledge injection into predictors via different algorithms. In particular, we discuss the overall architecture, and the many components/functionalities of PSyKI, invidually—providing examples as well. We finally demonstrate the versatility of our approach by exemplifying two custom injection algorithms in a toy scenario: Poker Hands classification
KINS: Knowledge Injection via Network Structuring
Full text linkWe propose a novel method to inject symbolic knowledge in form of Datalog formulæ into neural networks (NN), called KINS (Knowledge Injection via Network Structuring). The idea behind our method is to extend NN internal structure with ad-hoc layers built out the injected symbolic knowledge. KINS does not constrain NN to any specific architecture, neither requires logic formulæ to be ground. Moreover, it is robust w.r.t. both lack of data and imperfect/incomplete knowledge. Experiments are reported to demonstrate the potential of KINS
Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review
Full text linkIn this article, we focus on the opacity issue of sub-symbolic machine learning predictors by promoting two complementary activities—symbolic knowledge extraction (SKE) and symbolic knowledge injection (SKI)—from and into sub-symbolic predictors. We consider as symbolic any language being intelligible and interpretable for both humans and computers. Accordingly, we propose general meta-models for both SKE and SKI, along with two taxonomies for the classification of SKE and SKI methods. By adopting an explainable artificial intelligence (XAI) perspective, we highlight how such methods can be exploited to mitigate the aforementioned opacity issue. Our taxonomies are attained by surveying and classifying existing methods from the literature, following a systematic approach, and by generalising the results of previous surveys targeting specific sub-topics of either SKE or SKI alone. More precisely, we analyse 132 methods for SKE and 117 methods for SKI, and we categorise them according to their purpose, operation, expected input/output data and predictor types. For each method, we also indicate the presence/lack of runnable software implementations. Our work may be of interest for data scientists aiming at selecting the most adequate SKE/SKI method for their needs, and may also work as suggestions for researchers interested in filling the gaps of the current state-of-the-art as well as for developers willing to implement SKE/SKI-based technologies
Bridging Symbolic and Sub-Symbolic AI: Towards Cooperative Transfer Learning in Multi-Agent Systems
Full text linkCooperation and knowledge sharing are of paramount importance in the evolution of an intelligent species. Knowledge sharing requires a set of symbols with a shared interpretation, enabling effective communication supporting cooperation. The engineering of intelligent systems may then benefit from the distribution of knowledge among multiple components capable of cooperation and symbolic knowledge sharing. Accordingly, in this paper, we propose a roadmap for the exploitation of knowledge representation and sharing to foster higher degrees of artificial intelligence. We do so by envisioning intelligent systems as composed by multiple agents, capable of cooperative (transfer) learning—Co(T)L for short. In CoL, agents can improve their local (sub-symbolic) knowledge by exchanging (symbolic) information among each others. In CoTL, agents can also learn new tasks autonomously by sharing information about similar tasks. Along this line, we motivate the introduction of Co(T)L and discuss benefits and feasibility
Symbolic knowledge injection meets intelligent agents: QoS metrics and experiments
Full text linkBridging intelligent symbolic agents and sub-symbolic predictors is a long-standing research goal in AI. Among the recent integration efforts, symbolic knowledge injection (SKI) proposes algorithms aimed at steering sub-symbolic predictors’ learning towards compliance w.r.t. pre-existing symbolic knowledge bases. However, state-of-the-art contributions about SKI mostly tackle injection from a foundational perspective, often focussing solely on improving the predictive performance of the sub-symbolic predictors undergoing injection. Technical contributions, in turn, are tailored on individual methods/experiments and therefore poorly interoperable with agent technologies as well as among each others. Intelligent agents may exploit SKI to serve many purposes other than predictive performance alone—provided that, of course, adequate technological support exists: for instance, SKI may allow agents to tune computational, energetic, or data requirements of sub-symbolic predictors. Given that different algorithms may exist to serve all those many purposes, some criteria for algorithm selection as well as a suitable technology should be available to let agents dynamically select and exploit the most suitable algorithm for the problem at hand. Along this line, in this work we design a set of quality-of-service (QoS) metrics for SKI, and a general-purpose software API to enable their application to various SKI algorithms—namely, platform for symbolic knowledge injection (PSyKI). We provide an abstract formulation of four QoS metrics for SKI, and describe the design of PSyKI according to a software engineering perspective. Then we discuss how our QoS metrics are supported by PSyKI. Finally, we demonstrate the effectiveness of both our QoS metrics and PSyKI via a number of experiments, where SKI is both applied and assessed via our proposed API. Our empirical analysis demonstrates both the soundness of our proposed metrics and the versatility of PSyKI as the first software tool supporting the application, interchange, and numerical assessment of SKI techniques. To the best of our knowledge, our proposals represent the first attempt to introduce QoS metrics for SKI, and the software tools enabling their practical exploitation for both human and computational agents. In particular, our contributions could be exploited to automate and/or compare the manifold SKI algorithms from the state of the art. Hence moving a concrete step forward the engineering of efficient, robust, and trustworthy software applications that integrate symbolic agents and sub-symbolic predictors
An Empirical Study on the Robustness of Knowledge Injection Techniques Against Data Degradation
Full text linkSymbolic knowledge injection (SKI) represents a promising paradigm for bridging symbolic knowledge and sub-symbolic predictors in intelligent autonomous agents. Given the wide availability of SKI methods from the literature, we observe that SKI effectiveness is commonly measured in terms of predictive performance variation – e.g., accuracy improvement – introduced by SKI. However, other aspects such as the injection mechanism’s ability to maintain its performance and generalisation capability, despite encountering unexpected or anomalous input during the training process, are equally relevant. Accordingly, in this paper we propose a new metric to evaluate the robustness of SKI techniques, defined as a measure of performance degradation in response to systematic dataset variations. The proposed metric enables precise quantification of the robustness degree across injection approaches and different perturbations. Details on generating and quantifying perturbations are also provided. We evaluate the effectiveness of our metric through several experiments, where we apply multiple SKI techniques to three datasets and measure how robustness varies as perturbations increase
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
