In this paper, we investigate a novel digital network twin (DNT) assisted deep learning (DL) model training framework that enables a base station (BS) to select the data collection source from both physical network and DNT for training DL models used to optimize network performance. In particular, we consider a DNT enabled cellular network that consists of a physical network where a BS uses several antennas to serve multiple mobile users, and a DNT that is a virtual representation of the physical network. The BS must adjust the antenna tilt angles to optimize the data rates of all users. Due to the user mobility, the BS may not be able to accurately track the network dynamics. Hence, a reinforcement learning (RL) approach is used to dynamically adjust the antenna tilt angles. To train the RL, we can use data collected from the physical network and the DNT. The data collected from the physical network is more accurate but incurs more communication overhead compared to the data collected from the DNT. Therefore, it is necessary to determine the ratio of data collected from the physical network and the DNT to improve the training of the RL model, so as to optimize the tilt angle of each antenna in response to user mobility. We formulate an optimization problem to jointly optimize the tilt angle adjustment policy and the data collection strategy, aiming to maximize the data rates of all users while constraining the time delay introduced by collecting data from the physical network. To solve this optimization problem, we propose a hierarchical RL framework consisting of a two-level proximal policy optimization (PPO). The first level PPO dynamically adjusts the antenna tilt angles, and the second level PPO determines the ratio of data collected from the physical network to improve the first level PPO training performance. Compared to traditional single RL algorithms such as deep Q network (DQN), the designed method optimizes the data collection ratio and the antenna tilt angles at diverse time intervals, allowing the second level PPO to adjust the data collection ratio with a large timescale using the training information provided by the first level PPO, and allowing the first level PPO focuses on adjusting the antenna tilt angles with a small timescale. Simulation results show that our proposed method reduces the physical network data collection delay by up to 71.85% compared to a hierarchical RL that uses a deep deterministic policy gradient algorithm as the second level RL.

Secondary Carrier Prediction (SCP) is a data-driven Radio Access Network (RAN) feature that ensures the best possible cell and frequency carrier assignment to a User Equipment (UE), without the UE needing to perform an excessive amount of inter-frequency measurements and reporting. In this paper, we investigate if the performance of SCP can be further enhanced by jointly training it with other data-driven RAN tasks at the network edge in a Multi-Task Learning (MTL) fashion. We evaluate the trained SCP model performance when it runs a Mobility Load Balancing (MLB) downstream task under different task groupings. Results show that for the simulation scenario considered in this work, about 29.6% improvement in load balancing index is achieved when SCP is used in MTL mode over Single Task Learning (STL) mode during inference.

In explainable AI, many explanation methods generate similar yet diverging explanations for machine learning (ML) models. How fair is it then to explain ML model behaviour by such explanations? Arguably, one needs to judge whether those explanations are good at explaining ML model input/output behaviour. We here attempt to formalise ways to judge goodness of such explanations in terms of their correctness. For assessing correctness, one needs to have desirable properties of explanation correctness in mind, as well as was to measure satisfaction of those properties. We submit two high-level properties of soundness and completeness for assessing explanation correctness: explaining is sound if the model behaves the way the explanations say; explaining is complete if explanations can be given for model’s outputs on any inputs. We formulate soundness and completeness properties for three forms of explanations: feature importance, counterfactuals and rules. We further formalise multiple general metrics, at least one for each property and form of explanation, for quantitatively measuring satisfaction of soundness and completeness. We argue that explanations are correct in as much as various aspects of the different forms of explanations are met as quantified by those metrics. We hope that being able to assess correctness of ML model input/output behaviour explanations against formal properties and metrics is a substantial step towards fairly explaining ML-based inference.

This paper presents a formal approach to explaining change of inference in Quantitative Bipolar Argumentation Frameworks (QBAFs). When drawing conclusions from a QBAF and updating the QBAF to then again draw conclusions (and so on), our approach traces changes – which we call strength inconsistencies – in the partial order over argument strengths that a semantics establishes on some arguments of interest, called topic arguments. We trace the causes of strength inconsistencies to specific arguments, which then serve as explanations. We identify sufficient, necessary, and counterfactual explanations for strength inconsistencies and show that strength inconsistency explanations exist if and only if an update leads to strength inconsistency. We define a heuristic-based approach to facilitate the search for strength inconsistency explanations, for which we also provide an implementation.

We present a principle-based analysis of contribution functions for quantitative bipolar argumentation graphs that quantify the contribution of one argument to another. The introduced principles formalise the intuitions underlying different contribution functions as well as expectations one would have regarding the behaviour of contribution functions in general. As none of the covered contribution functions satisfies all principles, our analysis can serve as a tool that enables the selection of the most suitable function based on the requirements of a given use case.

As wireless cellular networks evolve from one generation to the next, the associated challenges in terms of compute, latency, and energy efficiency are continuously on the rise. However, traditional methods are unable to cope with the complexity of operation in next generation mobile networks, and the operational costs can become a significant hurdle in emerging generations. To address these issues, an AI-native wireless communication system is needed to support faster processing and optimization. Researchers have been exploring nature-inspired models for years to improve deep learning architectures, making them smaller, sparser, more efficient, and easily interpretable. In this study, we propose a nature-inspired Machine Learning architecture that leverages curriculum learning to predict cellular traffic on real wireless cellular network data. Our proposed architecture requires significantly fewer parameters to train, is 64% sparse and performs better than the standard state-of-the-art model. Here, sparsity refers to the fewer connections than the maximum possible number of connections within that network between each layer. Moreover, in terms of performance and carbon emissions, this sparsely connected architecture is better than traditional Machine Learning models.

This paper presents a formal approach to explaining change of inference in Quantitative Bipolar Argumentation Frameworks (QBAFs). When drawing conclusions from a QBAF and updating the QBAF to then again draw conclusions (and so on), our approach traces changes – which we call strength inconsistencies – in the partial order that a semantics establishes on the arguments in the QBAFs. We trace the strength inconsistencies to specific arguments, which then serve as explanations. We identify both sufficient and counterfactual explanations for strength inconsistencies and show that our approach guarantees that explanation arguments exist if and only if an update leads to strength inconsistency.

Explainable AI (XAI) has been investigated for decades and, together with AI itself, has witnessed unprecedented growth in recent years. Among various approaches to XAI, argumentative models have been advocated in both the AI and social science literature, as their dialectical nature appears to match some basic desirable features of the explanation activity. In this survey we overview XAI approaches built using methods from the field of computational argumentation, leveraging its wide array of reasoning abstractions and explanation delivery methods. We overview the literature focusing on different types of explanation (intrinsic and post-hoc), different models with which argumentation-based explanations are deployed, different forms of delivery, and different argumentation frameworks they use. We also lay out a roadmap for future work.

Today’s AI landscape is permeated by plentiful data anddominated by powerful data-centric methods with the potential toimpact a wide range of human sectors. Yet, in some settings this po-tential is hindered by these data-centric AI methods being mostlyopaque. Considerable efforts are currently being devoted to defin-ing methods for explaining black-box techniques in some settings,while the use of transparent methods is being advocated in others,especially when high-stake decisions are involved, as in healthcareand the practice of law. In this paper we advocate a novel transpar-ent paradigm of Data-Empowered Argumentation (DEAr in short)for dialectically explainable predictions. DEAr relies upon the ex-traction of argumentation debates from data, so that the dialecticaloutcomes of these debates amount to predictions (e.g. classifications)that can be explained dialectically. The argumentation debates con-sist of (data) arguments which may not be linguistic in general butmay nonetheless be deemed to be ‘arguments’ in that they are dialec-tically related, for instance by disagreeing on data labels. We illus-trate and experiment with the DEAr paradigm in three settings, mak-ing use, respectively, of categorical data, (annotated) images and text.We show empirically that DEAr is competitive with another transpar-ent model, namely decision trees (DTs), while also providing natu-rally dialectical explanations.

Mathematical optimization offers highly-effective tools for finding solutions for problems with well-defined goals, notably scheduling. However, optimization solvers are often unexplainable black boxes whose solutions are inaccessible to users and which users cannot interact with. We define a novel paradigm using argumentation to empower the interaction between optimization solvers and users, supported by tractable explanations which certify or refute solutions. A solution can be from a solver or of interest to a user (in the context of ‘what-if’ scenarios). Specifically, we define argumentative and natural language explanations for why a schedule is (not) feasible, (not) efficient or (not) satisfying fixed user decisions, based on models of the fundamental makespan scheduling problem in terms of abstract argumentation frameworks (AFs). We define three types of AFs, whose stable extensions are in one-to-one correspondence with schedules that are feasible, efficient and satisfying fixed decisions, respectively. We extract the argumentative explanations from these AFs and the natural language explanations from the argumentative ones.

Case-based reasoning (CBR) is extensively used in AI in support of several applications, to assess a new situation (or case) by recollecting past situations (or cases) and employing the ones most similar to the new situation to give the assessment. In this paper we study properties of a recently proposed method for CBR, based on instantiated Abstract Argumentation and referred to as AA-CBR, for problems where cases are represented by abstract factors and (positive or negative) outcomes, and an outcome for a new case, represented by abstract factors, needs to be established. In addition, we study properties of explanations in AA-CBR and define a new notion of lean explanations that utilize solely relevant cases. Both forms of explanations can be seen as dialogical processes between a proponent and an opponent, with the burden of proof falling on the proponent.