arXiv subjects

Nikolaos Pappas

Publications and source records attributed to Nikolaos Pappas.

At least 91 records · Page 5Linked to original sources

arXiv2024

Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models

The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this paper, and show that the challenge arises from the representation gap that emerges when introducing vision modality to VLMs. In particular, we show that the representations of multi-modal inputs shift away from that of text-only inputs which represent the distribution that the LLM backbone is optimized for. At the same time, the safety alignment capabilities, initially developed within the textual embedding space, do not successfully transfer to this new multi-modal representation space. To reduce safety alignment degradation, we introduce Cross-Modality Representation Manipulation (CMRM), an inference time representation intervention method for recovering the safety alignment ability that is inherent in the LLM backbone of VLMs, while simultaneously preserving the functional capabilities of VLMs. The empirical results show that our framework significantly recovers the alignment ability that is inherited from the LLM backbone with minimal impact on the fluency and linguistic capabilities of pre-trained VLMs even without additional training. Specifically, the unsafe rate of LLaVA-7B on multi-modal input can be reduced from 61.53% to as low as 3.15% with only inference-time intervention. WARNING: This paper contains examples of toxic or harmful language.

cs.CL↗

arXiv2024

MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets

Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous approaches augment textual dialogues with retrieved images, posing privacy, diversity, and quality constraints. In this work, we introduce Multimodal Augmented Generative Images Dialogues (MAGID), a framework to augment text-only dialogues with diverse and high-quality images. Subsequently, a diffusion model is applied to craft corresponding images, ensuring alignment with the identified text. Finally, MAGID incorporates an innovative feedback loop between an image description generation module (textual LLM) and image quality modules (addressing aesthetics, image-text matching, and safety), that work in tandem to generate high-quality and multi-modal dialogues. We compare MAGID to other SOTA baselines on three dialogue datasets, using automated and human evaluation. Our results show that MAGID is comparable to or better than baselines, with significant improvements in human evaluation, especially against retrieval baselines where the image database is small.

cs.CL↗

arXiv2024

Sequential Editing for Lifelong Training of Speech Recognition Models

Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on new domain risks Catastrophic Forgetting (CF). To address this, Lifelong Learning (LLL) algorithms have been proposed for ASR. Prior research has explored techniques such as Elastic Weight Consolidation, Knowledge Distillation, and Replay, all of which necessitate either additional parameters or access to prior domain data. We propose Sequential Model Editing as a novel method to continually learn new domains in ASR systems. Different than previous methods, our approach does not necessitate access to prior datasets or the introduction of extra parameters. Our study demonstrates up to 15% Word Error Rate Reduction (WERR) over fine-tuning baseline, and superior efficiency over other LLL techniques on CommonVoice English multi-accent dataset.

cs.CL↗

arXiv2024

Age of Information Versions: a Semantic View of Markov Source Monitoring

We consider the problem of real-time remote monitoring of a two-state Markov process, where a sensor observes the state of the source and makes a decision on whether to transmit the status updates over an unreliable channel or not. We introduce a modified randomized stationary sampling and transmission policy where the decision to perform sampling occurs probabilistically depending on the current state of the source and whether the system was in a sync state during the previous time slot or not. We then propose two new performance metrics, coined the Version Innovation Age (VIA) and the Age of Incorrect Version (AoIV) and analyze their performance under the modified randomized stationary and other state-of-the-art sampling and transmission policies. Specifically, we derive closed-form expressions for the distribution and the average of VIA, AoIV, and Age of Incorrect Information (AoII) under these policies. Furthermore, we formulate and solve three constrained optimization problems. The first optimization problem aims to minimize the average VIA subject to constraints on the time-averaged sampling cost and time-averaged reconstruction error. In the second and third problems, the objective is to minimize the average AoIV and AoII, respectively, while considering a constraint on the time-averaged sampling cost. Finally, we compare the performance of various sampling and transmission policies and identify the conditions under which each policy outperforms the others in optimizing the proposed metrics.

cs.IT↗

arXiv2024

Goal-Oriented Multiple Access Connectivity for Networked Intelligent Systems

We design a self-decision goal-oriented multiple access scheme, where sensing agents observe a common event and individually decide to communicate the event's attributes as updates to the monitoring agents, to satisfy a certain goal. Decisions are based on the usefulness of updates, generated under uniform, change- and semantics-aware acquisition, as well as statistics and updates of other agents. We obtain optimal activation probabilities and threshold criteria for decision-making under all schemes, maximizing a grade of effectiveness metric. Alongside studying the effect of different parameters on effectiveness, our simulation results show that the self-decision scheme may attain at least 92% of optimal performance.

cs.IT↗

arXiv2024

Eliciting Better Multilingual Structured Reasoning from LLMs through Code

The development of large language models (LLM) has shown progress on reasoning, though studies have largely considered either English or simple reasoning tasks. To address this, we introduce a multilingual structured reasoning and explanation dataset, termed xSTREET, that covers four tasks across six languages. xSTREET exposes a gap in base LLM performance between English and non-English reasoning tasks. We then propose two methods to remedy this gap, building on the insight that LLMs trained on code are better reasoners. First, at training time, we augment a code dataset with multilingual comments using machine translation while keeping program code as-is. Second, at inference time, we bridge the gap between training and inference by employing a prompt structure that incorporates step-by-step code primitives to derive new facts and find a solution. Our methods show improved multilingual performance on xSTREET, most notably on the scientific commonsense reasoning subtask. Furthermore, the models show no regression on non-reasoning tasks, thus demonstrating our techniques maintain general-purpose abilities.

cs.CL↗

arXiv2024

Age-Threshold Slotted ALOHA for Optimizing Information Freshness in Mobile Networks

We optimize the Age of Information (AoI) in mobile networks using the age-threshold slotted ALOHA (TSA) protocol. The network comprises multiple source-destination pairs, where each source sends a sequence of status update packets to its destination over a shared spectrum. The TSA protocol stipulates that a source node must remain silent until its AoI reaches a predefined threshold, after which the node accesses the radio channel with a certain probability. Using stochastic geometry tools, we derive analytical expressions for the transmission success probability, mean peak AoI, and time-average AoI. Subsequently, we obtain closed-form expressions for the optimal update rate and age threshold that minimize the mean peak and time-average AoI, respectively. In addition, we establish a scaling law for the mean peak AoI and time-average AoI in mobile networks, revealing that the optimal mean peak AoI and time-average AoI increase linearly with the deployment density. Notably, the growth rate of time-average AoI under TSA is half of that under conventional slotted ALOHA. When considering the optimal mean peak AoI, the TSA protocol exhibits comparable performance to the traditional slotted ALOHA protocol. These findings conclusively affirm the advantage of TSA in reducing higher-order AoI, particularly in densely deployed networks.

cs.NI↗

arXiv2024

Goal-oriented Estimation of Multiple Markov Sources in Resource-constrained Systems

This paper investigates goal-oriented communication for remote estimation of multiple Markov sources in resource-constrained networks. An agent decides the updating times of the sources and transmits the packet to a remote destination over an unreliable channel with delay. The destination is tasked with source reconstruction for actuation. We utilize the metric \textit{cost of actuation error} (CAE) to capture the state-dependent actuation costs. We aim for a sampling policy that minimizes the long-term average CAE subject to an average resource constraint. We formulate this problem as an average-cost constrained Markov Decision Process (CMDP) and relax it into an unconstrained problem by utilizing \textit{Lyapunov drift} techniques. Then, we propose a low-complexity \textit{drift-plus-penalty} (DPP) policy for systems with known source/channel statistics and a Lyapunov optimization-based deep reinforcement learning (LO-DRL) policy for unknown environments. Our policies significantly reduce the number of uninformative transmissions by exploiting the timing of the important information.

eess.SY↗

arXiv2024

Optimizing Information Freshness in IoT Systems with Update Rate Constraints: A Token-Based Approach

In Internet of Things (IoT) status update systems, where information is sampled and subsequently transmitted from a source to a destination node, the imperative necessity lies in maintaining the timeliness of information and updating the system with optimal frequency. Optimizing information freshness in resource-limited status update systems often involves Constrained Markov Decision Process (CMDP) problems with update rate constraints. Solving CMDP problems, especially with multiple constraints, is a challenging task. To address this, we present a token-based approach that transforms CMDP into an unconstrained MDP, simplifying the solution process. We apply this approach to systems with one and two update rate constraints for optimizing Age of Incorrect Information (AoII) and Age of Information (AoI) metrics, respectively, and explore the analytical and numerical aspects. Additionally, we introduce an iterative triangle bisection method for solving the CMDP problems with two constraints, comparing its results with the token-based MDP approach. Our findings show that the token-based approach yields superior performance over baseline policies, converging to the optimal policy as the maximum number of tokens increases.

cs.IT↗

arXiv2024

Timeliness of Status Update System: The Effect of Parallel Transmission Using Heterogeneous Updating Devices

Timely status updating is the premise of emerging interaction-based applications in the Internet of Things (IoT). Using redundant devices to update the status of interest is a promising method to improve the timeliness of information. However, parallel status updating leads to out-of-order arrivals at the monitor, significantly challenging timeliness analysis. This work studies the Age of Information (AoI) of a multi-queue status update system where multiple devices monitor the same physical process. Specifically, two systems are considered: the Basic System, which only has type-1 devices that are ad hoc devices located close to the source, and the Hybrid System, which contains additional type-2 devices that are infrastructure-based devices located in fixed points compared to the Basic System. Using the Stochastic Hybrid Systems (SHS) framework, a mathematical model that combines discrete and continuous dynamics, we derive the expressions of the average AoI of the considered two systems in closed form. Numerical results verify the accuracy of the analysis. It is shown that when the number and parameters of the type-1 devices/type-2 devices are fixed, the logarithm of average AoI will linearly decrease with the logarithm of the total arrival rate of type-2 devices or that of the number of type-1 devices under specific condition. It has also been demonstrated that the proposed systems can significantly outperform the FCFS M/M/N status update system.

cs.IT↗

arXiv2024

State-Aware Timeliness in Energy Harvesting IoT Systems Monitoring a Markovian Source

In this study, we investigate the optimal transmission policies within an energy harvesting status update system, where the demand for status updates depends on the state of the source. The system monitors a two-state Markovian source that characterizes a stochastic process, which can be in either a normal state or an alarm state, with a higher demand for fresh updates when the source is in the alarm state. We propose a metric to capture the freshness of status updates for each state of the stochastic process by introducing two Age of Information (AoI) variables, extending the definition of AoI to account for the state changes of the stochastic process. We formulate the problem as a Markov Decision Process (MDP), utilizing a transition cost function that applies linear and non-linear penalties based on AoI and the state of the stochastic process. Through analytical investigation, we delve into the structure of the optimal transmission policy for the resulting MDP problem. Furthermore, we evaluate the derived policies via numerical results and demonstrate their effectiveness in reserving energy in anticipation of forthcoming alarm states.

cs.IT↗

arXiv2024

Numeric Reward Machines

Reward machines inform reinforcement learning agents about the reward structure of the environment and often drastically speed up the learning process. However, reward machines only accept Boolean features such as robot-reached-gold. Consequently, many inherently numeric tasks cannot profit from the guidance offered by reward machines. To address this gap, we aim to extend reward machines with numeric features such as distance-to-gold. For this, we present two types of reward machines: numeric-Boolean and numeric. In a numeric-Boolean reward machine, distance-to-gold is emulated by two Boolean features distance-to-gold-decreased and robot-reached-gold. In a numeric reward machine, distance-to-gold is used directly alongside the Boolean feature robot-reached-gold. We compare our new approaches to a baseline reward machine in the Craft domain, where the numeric feature is the agent-to-target distance. We use cross-product Q-learning, Q-learning with counter-factual experiences, and the options framework for learning. Our experimental results show that our new approaches significantly outperform the baseline approach. Extending reward machines with numeric features opens up new possibilities of using reward machines in inherently numeric tasks.

cs.AI↗

arXiv2024

Goal-Oriented Semantic Communications for 6G Networks

Upon the arrival of emerging devices, including Extended Reality (XR) and Unmanned Aerial Vehicles (UAVs), the traditional communication framework is approaching Shannon's physical capacity limit and fails to guarantee the massive amount of transmission within latency requirements. By jointly exploiting the context of data and its importance to the task, an emerging communication paradigm shift to semantic level and effectiveness level is envisioned to be a key revolution in Sixth Generation (6G) networks. However, an explicit and systematic communication framework incorporating both semantic level and effectiveness level has not been proposed yet. In this article, we propose a generic goal-oriented semantic communication framework for various tasks with diverse data types, which incorporates both semantic level information and effectiveness-aware performance metrics. We first analyze the unique characteristics of all data types, and summarise the semantic information, along with corresponding extraction methods. We then propose a detailed goal-oriented semantic communication framework for different time-critical and non-critical tasks. In the goal-oriented semantic communication framework, we present the goal-oriented semantic information, extraction methods, recovery methods, and effectiveness-aware performance metrics. Last but not least, we present a goal-oriented semantic communication framework tailored for Unmanned Aerial Vehicle (UAV) control task to validate the effectiveness of the proposed goal-oriented semantic communication framework.

eess.SY↗

arXiv2024

Adaptive Federated Learning Over the Air

We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. This approach capitalizes on the inherent superposition property of wireless channels, facilitating fast and scalable parameter aggregation. Meanwhile, it enhances the robustness of the model training process by dynamically adjusting the stepsize in accordance with the global gradient update. We derive the convergence rate of the training algorithms, encompassing the effects of channel fading and interference, for a broad spectrum of nonconvex loss functions. Our analysis shows that the AdaGrad-based algorithm converges to a stationary point at the rate of $\mathcal{O}( \ln{(T)} /{ T^{ 1 - \frac{1}α } } )$, where $α$ represents the tail index of the electromagnetic interference. This result indicates that the level of heavy-tailedness in interference distribution plays a crucial role in the training efficiency: the heavier the tail, the slower the algorithm converges. In contrast, an Adam-like algorithm converges at the $\mathcal{O}( 1/T )$ rate, demonstrating its advantage in expediting the model training process. We conduct extensive experiments that corroborate our theoretical findings and affirm the practical efficacy of our proposed federated adaptive gradient methods.

cs.LG↗

arXiv2024

Semantic Text Transmission via Prediction with Small Language Models: Cost-Similarity Trade-off

We consider the communication of natural language text from a source to a destination over noiseless and character-erasure channels. We exploit language's inherent correlations and predictability to constrain transmission costs by allowing the destination to predict or complete words with potential dissimilarity with the source text. Concretely, our objective is to obtain achievable $(\bar{c}, \bar{s})$ pairs, where $\bar{c}$ is the average transmission cost at the source and $\bar{s}$ is the average semantic similarity measured via cosine similarity between vector embedding of words at the source and those predicted/completed at the destination. We obtain $(\bar{c}, \bar{s})$ pairs for neural language and first-order Markov chain-based small language models (SLM) for prediction, using both a threshold policy that transmits a word if its cosine similarity with that predicted/completed at the destination is below a threshold, and a periodic policy, which transmits words after a specific interval and predicts/completes the words in between, at the destination. We adopt an SLM for word completion. We demonstrate that, when communication occurs over a noiseless channel, the threshold policy achieves a higher $\bar{s}$ for a given $\bar{c}$ than the periodic policy and that the $\bar{s}$ achieved with the neural SLM is greater than or equal to that of the Markov chain-based algorithm for the same $\bar{c}$. The improved performance comes with a higher complexity in terms of time and computing requirements. However, when communication occurs over a character-erasure channel, all prediction algorithms and scheduling policies perform poorly. Furthermore, if character-level Huffman coding is used, the required $\bar{c}$ to achieve a given $\bar{s}$ is reduced, but the above observations still apply.

cs.IT↗

arXiv2024

Enabling Communication and Control Co-Design in 6G Networks

Networked control systems (NCSs), which are feedback control loops closed over a communication network, have been a popular research topic over the past decades. Numerous works in the literature propose novel algorithms and protocols with joint consideration of communication and control. However, the vast majority of the recent research results, which have shown remarkable performance improvements if a cross-layer methodology is followed, have not been widely adopted by the industry. In this work, we review the shortcomings of today's mobile networks that render cross-layer solutions, such as semantic and goal-oriented communications, very challenging in practice. To tackle this, we propose a new framework for 6G user plane design that simplifies the adoption of recent research results in networked control, thereby facilitating the joint communication and control design in next-generation mobile networks.

cs.NI↗

arXiv2024

Semantic Filtering and Source Coding in Distributed Wireless Monitoring Systems

The problem of goal-oriented semantic filtering and timely source coding in multiuser communication systems is considered here. We study a distributed monitoring system in which multiple information sources, each observing a physical process, provide status update packets to multiple monitors having heterogeneous goals. Two semantic filtering schemes are first proposed as a means to admit or drop arrival packets based on their goal-dependent importance, which is a function of the intrinsic and extrinsic attributes of information and the probability of occurrence of each realization. Admitted packets at each sensor are then encoded and transmitted over block-fading wireless channels so that served monitors can timely fulfill their goals. A truncated error control scheme is derived, which allows transmitters to drop or retransmit undelivered packets based on their significance. Then, we formulate the timely source encoding optimization problem and analytically derive the optimal codeword lengths assigned to the admitted packets which maximize a weighted sum of semantic utility functions for all pairs of communicating sensors and monitors. Our analytical and numerical results provide the optimal design parameters for different arrival rates and highlight the improvement in timely status update delivery using the proposed semantic filtering, source coding, and error control schemes.

cs.IT↗

arXiv2024

Effective Communication: When to Pull Updates?

We study a pull-based communication system where a sensing agent updates an actuation agent using a query control policy, which is adjusted in the evolution of an observed information source and the usefulness of each update for achieving a specific goal. For that, a controller decides whether to pull an update at each slot, predicting what is probably occurring at the source and how much effective impact that update could have at the endpoint. Thus, temporal changes in the source evolution could modify the query arrivals so as to capture important updates. The amount of impact is determined by a grade of effectiveness (GoE) metric, which incorporates both freshness and usefulness attributes of the communicated updates. Applying an iterative algorithm, we derive query decisions that maximize the long-term average GoE for the communicated packets, subject to cost constraints. Our analytical and numerical results show that the proposed query policy exhibits higher effectiveness than existing periodic and probabilistic query policies for a wide range of query arrival rates.

cs.IT↗