Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31195
Pei-Ying Lin, Erick Chandra, Jane Yung-jen Hsu
Commonsense reasoning refers to the ability to make inferences, draw conclusions, and understand the world based on general knowledge and commonsense. Whether Large Language Models (LLMs) have commonsense reasoning ability remains a topic of debate among researchers and experts. When confronted with multiple-choice commonsense reasoning tasks, humans typically rely on their prior knowledge and commonsense to formulate a preliminary answer in mind. Subsequently, they compare this preliminary answer to the provided choices, and select the most likely choice as the final answer. We introduce Aggregated Semantic Matching Retrieval (ASMR) as a solution for multiple-choice commonsense reasoning tasks. To mimic the process of humans solving commonsense reasoning tasks with multiple choices, we leverage the capabilities of LLMs to first generate the preliminary possible answers through open-ended question which aids in enhancing the process of retrieving relevant answers to the question from the given choices. Our experiments demonstrate the effectiveness of ASMR on popular commonsense reasoning benchmark datasets, including CSQA, SIQA, and ARC (Easy and Challenge). ASMR achieves state-of-the-art (SOTA) performance with a peak of +15.3% accuracy improvement over the previous SOTA on SIQA dataset.
{"title":"ASMR: Aggregated Semantic Matching Retrieval Unleashing Commonsense Ability of LLM through Open-Ended Question Answering","authors":"Pei-Ying Lin, Erick Chandra, Jane Yung-jen Hsu","doi":"10.1609/aaaiss.v3i1.31195","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31195","url":null,"abstract":"Commonsense reasoning refers to the ability to make inferences, draw conclusions, and understand the world based on general knowledge and commonsense. Whether Large Language Models (LLMs) have commonsense reasoning ability remains a topic of debate among researchers and experts. When confronted with multiple-choice commonsense reasoning tasks, humans typically rely on their prior knowledge and commonsense to formulate a preliminary answer in mind. Subsequently, they compare this preliminary answer to the provided choices, and select the most likely choice as the final answer. We introduce Aggregated Semantic Matching Retrieval (ASMR) as a solution for multiple-choice commonsense reasoning tasks. To mimic the process of humans solving commonsense reasoning tasks with multiple choices, we leverage the capabilities of LLMs to first generate the preliminary possible answers through open-ended question which aids in enhancing the process of retrieving relevant answers to the question from the given choices. Our experiments demonstrate the effectiveness of ASMR on popular commonsense reasoning benchmark datasets, including CSQA, SIQA, and ARC (Easy and Challenge). ASMR achieves state-of-the-art (SOTA) performance with a peak of +15.3% accuracy improvement over the previous SOTA on SIQA dataset.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141118926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31279
Shiwali Mohan, John E. Laird
Autonomous intelligent agents, including humans, operate in a complex, dynamic environment that necessitates continuous learning. We revisit our thesis that proposes that learning in human-like agents can be categorized into two levels: Level 1 (L1) involving innate and automatic learning mechanisms, while Level 2 (L2) comprises deliberate strategies controlled by the agent. Our thesis draws from our experiences in building artificial agents with complex learning behaviors, such as interactive task learning and open-world learning.
{"title":"Learning Fast and Slow: A Redux of Levels of Learning in General Autonomous Intelligent Agents","authors":"Shiwali Mohan, John E. Laird","doi":"10.1609/aaaiss.v3i1.31279","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31279","url":null,"abstract":"Autonomous intelligent agents, including humans, operate in a complex, dynamic environment that necessitates continuous learning. We revisit our thesis that proposes that learning in human-like agents can be categorized into two levels: Level 1 (L1) involving innate and automatic learning mechanisms, while Level 2 (L2) comprises deliberate strategies controlled by the agent. Our thesis draws from our experiences in building artificial agents with complex learning behaviors, such as interactive task learning and open-world learning.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120745","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31179
Simon Kapiamba, H. Fouad, Ira S. Moskowitz
This paper outlines an approach for assessing and quantifying the risks associated with integrating Large Language Models (LLMs) in generating naval operational plans. It aims to explore the potential benefits and challenges of LLMs in this context and to suggest a methodology for a comprehensive risk assessment framework.
{"title":"Responsible Integration of Large Language Models (LLMs) in Navy Operational Plan Generation","authors":"Simon Kapiamba, H. Fouad, Ira S. Moskowitz","doi":"10.1609/aaaiss.v3i1.31179","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31179","url":null,"abstract":"This paper outlines an approach for assessing and quantifying\u0000the risks associated with integrating Large Language Models\u0000(LLMs) in generating naval operational plans. It aims to explore\u0000the potential benefits and challenges of LLMs in this\u0000context and to suggest a methodology for a comprehensive\u0000risk assessment framework.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31218
Jithin Jagannath
Machine learning promises to empower dynamic resource allocation requirements of Next Generation (NextG) wireless networks including 6G and tactical networks. Recently, we have seen the impact machine learning can make on various aspects of wireless networks. Yet, in most cases, the progress has been limited to simulations and/or relies on large processing units to run the decision engines as opposed to deploying it on the radio at the edge. While relying on simulations for rapid and efficient training of deep reinforcement learning (DRL) may be necessary, it is key to mitigate the sim-real gap while trying to improve the generalization capability. To mitigate these challenges, we developed the Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym), an open-source architecture designed for accelerating the deployment of novel DRL for NextG wireless networks. To demonstrate its impact, we tackled the problem of distributed frequency and power allocation while emphasizing the generalization capability of DRL decision engine. The end-to-end solution was implemented on the GPU-embedded software-defined radio and validated using over-the-air evaluation. To the best of our knowledge, these were the first instances that established the feasibility of deploying DRL for optimized distributed resource allocation for next-generation of GPU-embedded radios.
{"title":"Framework for Federated Learning and Edge Deployment of Real-Time Reinforcement Learning Decision Engine on Software Defined Radio","authors":"Jithin Jagannath","doi":"10.1609/aaaiss.v3i1.31218","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31218","url":null,"abstract":"Machine learning promises to empower dynamic resource allocation requirements of Next Generation (NextG) wireless networks including 6G and tactical networks. Recently, we have seen the impact machine learning can make on various aspects of wireless networks. Yet, in most cases, the progress has been limited to simulations and/or relies on large processing units to run the decision engines as opposed to deploying it on the radio at the edge. While relying on simulations for rapid and efficient training of deep reinforcement learning (DRL) may be necessary, it is key to mitigate the sim-real gap while trying to improve the generalization capability. To mitigate these challenges, we developed the Marconi-Rosenblatt Framework for Intelligent Networks (MR-iNet Gym), an open-source architecture designed for accelerating the deployment of novel DRL for NextG wireless networks. To demonstrate its impact, we tackled the problem of distributed frequency and power allocation while emphasizing the generalization capability of DRL decision engine. The end-to-end solution was implemented on the GPU-embedded software-defined radio and validated using over-the-air evaluation. To the best of our knowledge, these were the first instances that established the feasibility of deploying DRL for optimized distributed resource allocation for next-generation of GPU-embedded radios.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31191
Nicholas Harvel, F. B. Haiek, Anupriya Ankolekar, David James Brunner
Large Language Models (LLMs) can increase the productivity of general-purpose knowledge work, but accuracy is a concern, especially in professional settings requiring domain-specific knowledge and reasoning. To evaluate the suitability of LLMs for such work, we developed a benchmark of 16 analytical tasks representative of the investment banking industry. We evaluated LLM performance without special prompting, with relevant information provided in the prompt, and as part of a system giving the LLM access to domain-tuned functions for information retrieval and planning. Without access to functions, state-of-the-art LLMs performed poorly, completing two or fewer tasks correctly. Access to appropriate domain-tuned functions yielded dramatically better results, although performance was highly sensitive to the design of the functions and the structure of the information they returned. The most effective designs yielded correct answers on 12 out of 16 tasks. Our results suggest that domain-specific functions and information structures, by empowering LLMs with relevant domain knowledge and enabling them to reason in domain-appropriate ways, may be a powerful means of adapting LLMs for use in demanding professional settings.
{"title":"Can LLMs Answer Investment Banking Questions? Using Domain-Tuned Functions to Improve LLM Performance on Knowledge-Intensive Analytical Tasks","authors":"Nicholas Harvel, F. B. Haiek, Anupriya Ankolekar, David James Brunner","doi":"10.1609/aaaiss.v3i1.31191","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31191","url":null,"abstract":"Large Language Models (LLMs) can increase the productivity of general-purpose knowledge work, but accuracy is a concern, especially in professional settings requiring domain-specific knowledge and reasoning. To evaluate the suitability of LLMs for such work, we developed a benchmark of 16 analytical tasks representative of the investment banking industry. We evaluated LLM performance without special prompting, with relevant information provided in the prompt, and as part of a system giving the LLM access to domain-tuned functions for information retrieval and planning. Without access to functions, state-of-the-art LLMs performed poorly, completing two or fewer tasks correctly. Access to appropriate domain-tuned functions yielded dramatically better results, although performance was highly sensitive to the design of the functions and the structure of the information they returned. The most effective designs yielded correct answers on 12 out of 16 tasks. Our results suggest that domain-specific functions and information structures, by empowering LLMs with relevant domain knowledge and enabling them to reason in domain-appropriate ways, may be a powerful means of adapting LLMs for use in demanding professional settings.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31181
Stephen Russell, Fabio Montes Suros, Ashwin Kumar
For a large healthcare system, ignoring costs associated with managing the patient encounter denial process (staffing, contracts, etc.), total denial-related amounts can be more than $1B annually in gross charges. Being able to predict a denial before it occurs has the potential for tremendous savings. Using machine learning to predict denial has the potential to allow denial-preventing interventions. However, challenges of data imbalance make creating a single generalized model difficult. We employ two biased models in a hybrid voting scheme to achieve results that exceed the state-of-the art and allow for incremental predictions as the encounter progresses. The model had the added benefit of monitoring the human-driven denial process that affect the underlying distribution, on which the models’ bias is based.
{"title":"Exploiting Machine Learning Bias: Predicting Medical Denials","authors":"Stephen Russell, Fabio Montes Suros, Ashwin Kumar","doi":"10.1609/aaaiss.v3i1.31181","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31181","url":null,"abstract":"For a large healthcare system, ignoring costs associated with managing the patient encounter denial process (staffing, contracts, etc.), total denial-related amounts can be more than $1B annually in gross charges. Being able to predict a denial before it occurs has the potential for tremendous savings. Using machine learning to predict denial has the potential to allow denial-preventing interventions. However, challenges of data imbalance make creating a single generalized model difficult. We employ two biased models in a hybrid voting scheme to achieve results that exceed the state-of-the art and allow for incremental predictions as the encounter progresses. The model had the added benefit of monitoring the human-driven denial process that affect the underlying distribution, on which the models’ bias is based.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141123298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31259
Yu Chen, Gabriel Granco, Yunfei Hou, Heather Macias, Frank A. Gomez
This project aims to broaden AI education by developing and studying the efficacy of innovative learning practices and resources for AI education for social good. We have developed three AI learning modules for students to: 1) identify social issues that align with the SDGs in their community (e.g., poverty, hunger, quality education); 2) learn AI through hands-on labs and business applications; and 3) create AI-powered solutions in teams to address social is-sues they have identified. Student teams are expected to situate AI learning in their communities and contribute to their communities. Students then use the modules to en-gage in an interdisciplinary approach, facilitating AI learn-ing for social good in informational sciences and technology, geography, and computer science at three CSU HSIs (San Jose State University, Cal Poly Pomona and CSU San Bernardino). Finally, we aim to evaluate the efficacy and impact of the proposed AI teaching methods and activities in terms of learning outcomes, student experience, student engagement, and equity.
{"title":"AI for Social Good Education at Hispanic Serving Institutions","authors":"Yu Chen, Gabriel Granco, Yunfei Hou, Heather Macias, Frank A. Gomez","doi":"10.1609/aaaiss.v3i1.31259","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31259","url":null,"abstract":"This project aims to broaden AI education by developing and studying the efficacy of innovative learning practices and resources for AI education for social good. We have developed three AI learning modules for students to: 1) identify social issues that align with the SDGs in their community (e.g., poverty, hunger, quality education); 2) learn AI through hands-on labs and business applications; and 3) create AI-powered solutions in teams to address social is-sues they have identified. Student teams are expected to situate AI learning in their communities and contribute to their communities. Students then use the modules to en-gage in an interdisciplinary approach, facilitating AI learn-ing for social good in informational sciences and technology, geography, and computer science at three CSU HSIs (San Jose State University, Cal Poly Pomona and CSU San Bernardino). Finally, we aim to evaluate the efficacy and impact of the proposed AI teaching methods and activities in terms of learning outcomes, student experience, student engagement, and equity.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141119091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31275
Peter Lindes, Steven Jones
Humans acquire language and related concepts in a trajectory over a lifetime. Concepts for simple interaction with the world are learned before language. Later, words are learned to name these concepts along with structures needed to represent larger meanings. Eventually, language advances to where it can drive the learning of new concepts. Throughout this trajectory a language processing capability uses architectural mechanisms to process language using the knowledge already acquired. We assume that this growing body of knowledge is made up of small units of form-meaning mapping that can be composed in many ways, suggesting that these units are learned incrementally from experience. In prior work we have built a system to comprehend human language within an autonomous robot using knowledge in such units developed by hand. Here we propose a research program to develop the ability of an artificial agent to acquire this knowledge incrementally and autonomously from its experience in a similar trajectory. We then propose a strategy for evaluating this human-like learning system using a large benchmark created as a tool for training deep learning systems. We expect that our human-like learning system will produce better task performance from training on only a small subset of this benchmark.
{"title":"Modeling Human-Like Acquisition of Language and Concepts","authors":"Peter Lindes, Steven Jones","doi":"10.1609/aaaiss.v3i1.31275","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31275","url":null,"abstract":"Humans acquire language and related concepts in a trajectory over a lifetime. Concepts for simple interaction with the world are learned before language. Later, words are learned to name these concepts along with structures needed to represent larger meanings. Eventually, language advances to where it can drive the learning of new concepts. Throughout this trajectory a language processing capability uses architectural mechanisms to process language using the knowledge already acquired. We assume that this growing body of knowledge is made up of small units of form-meaning mapping that can be composed in many ways, suggesting that these units are learned incrementally from experience. In prior work we have built a system to comprehend human language within an autonomous robot using knowledge in such units developed by hand. Here we propose a research program to develop the ability of an artificial agent to acquire this knowledge incrementally and autonomously from its experience in a similar trajectory. We then propose a strategy for evaluating this human-like learning system using a large benchmark created as a tool for training deep learning systems. We expect that our human-like learning system will produce better task performance from training on only a small subset of this benchmark.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31238
Yuto Nakashima
Generating preferred images from GANs is a challenging task due to the high-dimensional nature of latent space. In this study, we propose a novel approach that uses simple user-swipe interactions to generate preferred images from users. To effectively explore the latent space with only swipe interactions, we apply principal component analysis to the latent space of StyleGAN, creating meaningful subspaces. Additionally, we use a multi-armed bandit algorithm to decide which dimensions to explore, focusing on the user's preferences. Our experiments show that our method is more efficient in generating preferred images than the baseline.
由于潜在空间的高维特性，从 GAN 生成首选图像是一项具有挑战性的任务。在本研究中，我们提出了一种新方法，利用简单的用户滑动交互从用户生成首选图片。为了有效地利用刷卡交互探索潜在空间，我们对 StyleGAN 的潜在空间进行了主成分分析，从而创建了有意义的子空间。此外，我们还使用多臂匪徒算法来决定探索哪些维度，重点关注用户的偏好。实验表明，我们的方法在生成首选图片方面比基线方法更有效。
{"title":"Personalized Image Generation Through Swiping","authors":"Yuto Nakashima","doi":"10.1609/aaaiss.v3i1.31238","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31238","url":null,"abstract":"Generating preferred images from GANs is a challenging task due to the high-dimensional nature of latent space. In this study, we propose a novel approach that uses simple user-swipe interactions to generate preferred images from users. To effectively explore the latent space with only swipe interactions, we apply principal component analysis to the latent space of StyleGAN, creating meaningful subspaces. Additionally, we use a multi-armed bandit algorithm to decide which dimensions to explore, focusing on the user's preferences. Our experiments show that our method is more efficient in generating preferred images than the baseline.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-05-20DOI: 10.1609/aaaiss.v3i1.31200
Orfeas Menis Mastromichalakis, Edmund Dervakos, A. Chortaras, G. Stamou
The use of symbolic knowledge representation and reasoning as a way to resolve the lack of transparency of machine learning classifiers is a research area that has lately gained a lot of traction. In this work, we use knowledge graphs as the underlying framework providing the terminology for representing explanations for the operation of a machine learning classifier escaping the constraints of using the features of raw data as a means to express the explanations, providing a promising solution to the problem of the understandability of explanations. In particular, given a description of the application domain of the classifier in the form of a knowledge graph, we introduce a novel theoretical framework for representing explanations of its operation, in the form of query-based rules expressed in the terminology of the knowledge graph. This allows for explaining opaque black-box classifiers, using terminology and information that is independent of the features of the classifier and its domain of application, leading to more understandable explanations but also allowing the creation of different levels of explanations according to the final end-user.
{"title":"Rule-Based Explanations of Machine Learning Classifiers Using Knowledge Graphs","authors":"Orfeas Menis Mastromichalakis, Edmund Dervakos, A. Chortaras, G. Stamou","doi":"10.1609/aaaiss.v3i1.31200","DOIUrl":"https://doi.org/10.1609/aaaiss.v3i1.31200","url":null,"abstract":"The use of symbolic knowledge representation and reasoning as a way to resolve the lack of transparency of machine learning classifiers is a research area that has lately gained a lot of traction. In this work, we use knowledge graphs as the underlying framework providing the terminology for representing explanations for the operation of a machine learning classifier escaping the constraints of using the features of raw data as a means to express the explanations, providing a promising solution to the problem of the understandability of explanations. In particular, given a description of the application domain of the classifier in the form of a knowledge graph, we introduce a novel theoretical framework for representing explanations of its operation, in the form of query-based rules expressed in the terminology of the knowledge graph. This allows for explaining opaque black-box classifiers, using terminology and information that is independent of the features of the classifier and its domain of application, leading to more understandable explanations but also allowing the creation of different levels of explanations according to the final end-user.","PeriodicalId":516827,"journal":{"name":"Proceedings of the AAAI Symposium Series","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：