arXiv subjects

Suman Banerjee

Publications and source records attributed to Suman Banerjee.

At least 55 records · Page 3Linked to original sources

arXiv2025

Influential Slot and Tag Selection in Billboard Advertisement

The selection of influential billboard slots remains an important problem in billboard advertisements. Existing studies on this problem have not considered the case of context-specific influence probability. To bridge this gap, in this paper, we introduce the Context Dependent Influential Billboard Slot Selection Problem. First, we show that the problem is NP-hard. We also show that the influence function holds the bi-monotonicity, bi-submodularity, and non-negativity properties. We propose an orthant-wise Stochastic Greedy approach to solve this problem. We show that this method leads to a constant-factor approximation guarantee. Subsequently, we propose an orthant-wise Incremental and Lazy Greedy approach. In a generic sense, this is a method for maximizing a bi-submodular function under the cardinality constraint, which may also be of independent interest. We analyze the performance guarantee of this algorithm as well as time and space complexity. The proposed solution approaches have been implemented with real-world billboard and trajectory datasets. We compare the performance of our method with several baseline methods, and the results are reported. Our proposed orthant-wise stochastic greedy approach leads to significant results when the parameters are set properly with reasonable computational overhead.

cs.DS↗

arXiv2025

Group Trip Planning Query Problem with Multimodal Journey

In Group Trip Planning (GTP) Query Problem, we are given a city road network where a number of Points of Interest (PoI) have been marked with their respective categories (e.g., Cafeteria, Park, Movie Theater, etc.). A group of agents want to visit one PoI from every category from their respective starting location and once finished, they want to reach their respective destinations. This problem asks which PoI from every category should be chosen so that the aggregated travel cost of the group is minimized. This problem has been studied extensively in the last decade, and several solution approaches have been proposed. However, to the best of our knowledge, none of the existing studies have considered the different modalities of the journey, which makes the problem more practical. To bridge this gap, we introduce and study the GTP Query Problem with Multimodal Journey in this paper. Along with the other inputs of the GTP Query Problem, we are also given the different modalities of the journey that are available and their respective cost. Now, the problem is not only to select the PoIs from respective categories but also to select the modality of the journey. For this problem, we have proposed an efficient solution approach, which has been analyzed to understand their time and space requirements. A large number of experiments have been conducted using real-life datasets and the results have been reported. From the results, we observe that the PoIs and modality of journey recommended by the proposed solution approach lead to much less time and cost than the baseline methods.

cs.MA↗

arXiv2025

SwinGS: Sliding Window Gaussian Splatting for Volumetric Video Streaming with Arbitrary Length

Recent advances in 3D Gaussian Splatting (3DGS) have garnered significant attention in computer vision and computer graphics due to its high rendering speed and remarkable quality. While extant research has endeavored to extend the application of 3DGS from static to dynamic scenes, such efforts have been consistently impeded by excessive model sizes, constraints on video duration, and content deviation. These limitations significantly compromise the streamability of dynamic 3D Gaussian models, thereby restricting their utility in downstream applications, including volumetric video, autonomous vehicle, and immersive technologies such as virtual, augmented, and mixed reality. This paper introduces SwinGS, a novel framework for training, delivering, and rendering volumetric video in a real-time streaming fashion. To address the aforementioned challenges and enhance streamability, SwinGS integrates spacetime Gaussian with Markov Chain Monte Carlo (MCMC) to adapt the model to fit various 3D scenes across frames, in the meantime employing a sliding window captures Gaussian snapshots for each frame in an accumulative way. We implement a prototype of SwinGS and demonstrate its streamability across various datasets and scenes. Additionally, we develop an interactive WebGL viewer enabling real-time volumetric video playback on most devices with modern browsers, including smartphones and tablets. Experimental results show that SwinGS reduces transmission costs by 83.6% compared to previous work and could be easily scaled to volumetric videos with arbitrary length with no increasing of required GPU resources.

cs.MM↗

arXiv2025

A Regret-Aware Framework for Effective Social Media Advertising

Social Media Advertisement has emerged as an effective approach for promoting the brands of a commercial house. Hence, many of them have started using this medium to maximize the influence among the users and create a customer base. In recent times, several companies have emerged as Influence Provider who provides views of advertisement content depending on the budget provided by the commercial house. In this process, the influence provider tries to exploit the information diffusion phenomenon of a social network, and a limited number of highly influential users are chosen and activated initially. Due to diffusion phenomenon, the hope is that the advertisement content will reach a large number of people. Now, consider that a group of advertisers is approaching an influence provider with their respective budget and influence demand. Now, for any advertiser, if the influence provider provides more or less influence, it will be a loss for the influence provider. It is an important problem from the point of view of influence provider, as it is important to allocate the seed nodes to the advertisers so that the loss is minimized. In this paper, we study this problem, which we formally referred to as Regret Minimization in Social Media Advertisement Problem. We propose a noble regret model that captures the aggregated loss encountered by the influence provider while allocating the seed nodes. We have shown that this problem is a computationally hard problem to solve. We have proposed three efficient heuristic solutions to solve our problem, analyzed to understand their time and space requirements. They have been implemented with real world social network datasets, and several experiments have been conducted and compared to many baseline methods.

cs.SI↗

arXiv2025

Babel: A Scalable Pre-trained Model for Multi-Modal Sensing via Expandable Modality Alignment

This paper presents Babel, the expandable modality alignment model, specially designed for multi-modal sensing. While there has been considerable work on multi-modality alignment, they all struggle to effectively incorporate multiple sensing modalities due to the data scarcity constraints. How to utilize multi-modal data with partial pairings in sensing remains an unresolved challenge. Babel tackles this challenge by introducing the concept of expandable modality alignment. The key idea involves transforming the N-modality alignment into a series of binary-modality alignments. Novel techniques are also proposed to further mitigate data scarcity issue and balance the contribution of the newly incorporated modality with the previously established modality alignment during the expandable alignment process. We provide the comprehensive implementation. In the pre-training phase, Babel currently aligns 6 sensing modalities, namely Wi-Fi, mmWave, IMU, LiDAR, video, and depth. For the deployment phase, as a foundation model, any single or combination of aligned modalities could be selected from Babel and applied to downstream tasks. Evaluation demonstrates Babel's outstanding performance on eight human activity recognition datasets, compared to a broad range of baselines e.g., the SOTA single-modal sensing networks, multi-modal sensing framework, and multi-modal large language models. Babel not only improves the performance of individual modality sensing (12% averaged accuracy improvement), but also effectively fuses multiple available modalities (up to 22% accuracy increase). Case studies also highlight emerging application scenarios empowered by Babel, including cross-modality retrieval (i.e., sensing imaging), and bridging LLM for sensing comprehension.

cs.AI↗

arXiv2025

"Impressively Scary:" Exploring User Perceptions and Reactions to Unraveling Machine Learning Models in Social Media Applications

Machine learning models deployed locally on social media applications are used for features, such as face filters which read faces in-real time, and they expose sensitive attributes to the apps. However, the deployment of machine learning models, e.g., when, where, and how they are used, in social media applications is opaque to users. We aim to address this inconsistency and investigate how social media user perceptions and behaviors change once exposed to these models. We conducted user studies (N=21) and found that participants were unaware to both what the models output and when the models were used in Instagram and TikTok, two major social media platforms. In response to being exposed to the models' functionality, we observed long term behavior changes in 8 participants. Our analysis uncovers the challenges and opportunities in providing transparency for machine learning models that interact with local user data.

cs.HC↗

arXiv2025

AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection

The rapid advancements in Large Language Models (LLMs) have enabled their deployment as autonomous agents for handling complex tasks in dynamic environments. These LLMs demonstrate strong problem-solving capabilities and adaptability to multifaceted scenarios. However, their use as agents also introduces significant risks, including task-specific risks, which are identified by the agent administrator based on the specific task requirements and constraints, and systemic risks, which stem from vulnerabilities in their design or interactions, potentially compromising confidentiality, integrity, or availability (CIA) of information and triggering security risks. Existing defense agencies fail to adaptively and effectively mitigate these risks. In this paper, we propose AGrail, a lifelong agent guardrail to enhance LLM agent safety, which features adaptive safety check generation, effective safety check optimization, and tool compatibility and flexibility. Extensive experiments demonstrate that AGrail not only achieves strong performance against task-specific and system risks but also exhibits transferability across different LLM agents' tasks.

cs.AI↗

arXiv2025

Fairness Driven Slot Allocation Problem in Billboard Advertisement

In billboard advertisement, a number of digital billboards are owned by an influence provider, and several commercial houses (which we call advertisers) approach the influence provider for a specific number of views of their advertisement content on a payment basis. Though the billboard slot allocation problem has been studied in the literature, this problem still needs to be addressed from a fairness point of view. In this paper, we introduce the Fair Billboard Slot Allocation Problem, where the objective is to allocate a given set of billboard slots among a group of advertisers based on their demands fairly and efficiently. As fairness criteria, we consider the maximin fair share, which ensures that each advertiser will receive a subset of slots that maximizes the minimum share for all the advertisers. We have proposed a solution approach that generates an allocation and provides an approximate maximum fair share. The proposed methodology has been analyzed to understand its time and space requirements and a performance guarantee. It has been implemented with real-world trajectory and billboard datasets, and the results have been reported. The results show that the proposed approach leads to a balanced allocation by satisfying the maximin fairness criteria. At the same time, it maximizes the utility of advertisers.

cs.GT↗

arXiv2025

PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms

Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy concerns or impractical due to network connection. Recent advancements (MLC, 2023a; Gerganov, 2023) have facilitated the local deployment of LLMs. However, local deployment also presents challenges, particularly in balancing quality (generative performance), latency, and throughput within the hardware constraints of mobile devices. In this paper, we introduce our lightweight, all-in-one automated benchmarking framework that allows users to evaluate LLMs on mobile devices. We provide a comprehensive benchmark of various popular LLMs with different quantization configurations (both weights and activations) across multiple mobile platforms with varying hardware capabilities. Unlike traditional benchmarks that assess full-scale models on high-end GPU clusters, we focus on evaluating resource efficiency (memory and power consumption) and harmful output for compressed models on mobile devices. Our key observations include i) differences in energy efficiency and throughput across mobile platforms; ii) the impact of quantization on memory usage, GPU execution time, and power consumption; and iii) accuracy and performance degradation of quantized models compared to their non-quantized counterparts; and iv) the frequency of hallucinations and toxic content generated by compressed LLMs on mobile devices.

cs.LG↗

arXiv2024

Gemini: Integrating Full-fledged Sensing upon Millimeter Wave Communications

Integrating millimeter wave (mmWave)technology in both communication and sensing is promising as it enables the reuse of existing spectrum and infrastructure without draining resources. Most existing systems piggyback sensing onto conventional communication modes without fully exploiting the potential of integrated sensing and communication (ISAC) in mmWave radios (not full-fledged). In this paper, we design and implement a full-fledged mmWave ISAC system Gemini; it delivers raw channel states to serve a broad category of sensing applications. We first propose the mmWave self-interference cancellation approach to extract the weak reflected signals for near-field sensing purposes. Then, we develop a joint optimization scheduling framework that can be utilized in accurate radar sensing while maximizing the communication throughput. Finally, we design a united fusion sensing algorithm to offer a better sensing performance via combining monostatic and bistatic modes. We evaluate our system in extensive experiments to demonstrate Gemini's capability of simultaneously operating sensing and communication, enabling mmWave ISAC to perform better than the commercial off-the-shelf mmWave radar for 5G cellular networks.

cs.NI↗

arXiv2024

Multi-Slot Tag Assignment Problem in Billboard Advertisement

Nowadays, billboard advertising has emerged as an effective advertising technique due to higher returns on investment. Given a set of selected slots and tags, how to effectively assign the tags to the slots remains an important question. In this paper, we study the problem of assigning tags to the slots such that the number of tags for which influence demand of each zone is satisfied gets maximized. Formally, we call this problem the Multi-Slot Tag Assignment Problem. The input to the problem is a geographical region partitioned into several zones, a set of selected tags and slots, a trajectory, a billboard database, and the influence demand for every tag for each zone. The task here is to find out the assignment of tags to the slots, such the number of tags for which the zonal influence demand is satisfied is maximized. We show that the problem is NP-hard, and we propose an efficient approximation algorithm to solve this problem. A time and space complexity analysis of the proposed methodology has been done. The proposed methodology has been implemented with real-life datasets, and a number of experiments have been carried out to show the effectiveness and efficiency of the proposed approach. The obtained results have been compared with the baseline methods, and we observe that the proposed approach leads to a number of tags whose zonal influence demand is satisfied.

cs.DS↗

arXiv2024

An Effective Tag Assignment Approach for Billboard Advertisement

Billboard Advertisement has gained popularity due to its significant outrage in return on investment. To make this advertisement approach more effective, the relevant information about the product needs to be reached to the relevant set of people. This can be achieved if the relevant set of tags can be mapped to the correct slots. Formally, we call this problem the Tag Assignment Problem in Billboard Advertisement. Given trajectory, billboard database, and a set of selected billboard slots and tags, this problem asks to output a mapping of selected tags to the selected slots so that the influence is maximized. We model this as a variant of traditional bipartite matching called One-To-Many Bipartite Matching (OMBM). Unlike traditional bipartite matching, a tag can be assigned to only one slot; in the OMBM, a tag can be assigned to multiple slots while the vice versa can not happen. We propose an iterative solution approach that incrementally allocates the tags to the slots. The proposed methodology has been explained with an illustrated example. A complexity analysis of the proposed solution approach has also been conducted. The experimental results on real-world trajectory and billboard datasets prove our claim on the effectiveness and efficiency of the proposed solution.

cs.DS↗

arXiv2024

Buffer-based Gradient Projection for Continual Federated Learning

Continual Federated Learning (CFL) is essential for enabling real-world applications where multiple decentralized clients adaptively learn from continuous data streams. A significant challenge in CFL is mitigating catastrophic forgetting, where models lose previously acquired knowledge when learning new information. Existing approaches often face difficulties due to the constraints of device storage capacities and the heterogeneous nature of data distributions among clients. While some CFL algorithms have addressed these challenges, they frequently rely on unrealistic assumptions about the availability of task boundaries (i.e., knowing when new tasks begin). To address these limitations, we introduce Fed-A-GEM, a federated adaptation of the A-GEM method (Chaudhry et al., 2019), which employs a buffer-based gradient projection approach. Fed-A-GEM alleviates catastrophic forgetting by leveraging local buffer samples and aggregated buffer gradients, thus preserving knowledge across multiple clients. Our method is combined with existing CFL techniques, enhancing their performance in the CFL context. Our experiments on standard benchmarks show consistent performance improvements across diverse scenarios. For example, in a task-incremental learning scenario using the CIFAR-100 dataset, our method can increase the accuracy by up to 27%. Our code is available at https://github.com/shenghongdai/Fed-A-GEM.

cs.LG↗

arXiv2024

Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMM

Opinion summarization in e-commerce encapsulates the collective views of numerous users about a product based on their reviews. Typically, a product on an e-commerce platform has thousands of reviews, each review comprising around 10-15 words. While Large Language Models (LLMs) have shown proficiency in summarization tasks, they struggle to handle such a large volume of reviews due to context limitations. To mitigate, we propose a scalable framework called Xl-OpSumm that generates summaries incrementally. However, the existing test set, AMASUM has only 560 reviews per product on average. Due to the lack of a test set with thousands of reviews, we created a new test set called Xl-Flipkart by gathering data from the Flipkart website and generating summaries using GPT-4. Through various automatic evaluations and extensive analysis, we evaluated the framework's efficiency on two datasets, AMASUM and Xl-Flipkart. Experimental results show that our framework, Xl-OpSumm powered by Llama-3-8B-8k, achieves an average ROUGE-1 F1 gain of 4.38% and a ROUGE-L F1 gain of 3.70% over the next best-performing model.

cs.CL↗

arXiv2024

One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation

Evaluation of opinion summaries using conventional reference-based metrics rarely provides a holistic evaluation and has been shown to have a relatively low correlation with human judgments. Recent studies suggest using Large Language Models (LLMs) as reference-free metrics for NLG evaluation, however, they remain unexplored for opinion summary evaluation. Moreover, limited opinion summary evaluation datasets inhibit progress. To address this, we release the SUMMEVAL-OP dataset covering 7 dimensions related to the evaluation of opinion summaries: fluency, coherence, relevance, faithfulness, aspect coverage, sentiment consistency, and specificity. We investigate Op-I-Prompt a dimension-independent prompt, and Op-Prompts, a dimension-dependent set of prompts for opinion summary evaluation. Experiments indicate that Op-I-Prompt emerges as a good alternative for evaluating opinion summaries achieving an average Spearman correlation of 0.70 with humans, outperforming all previous approaches. To the best of our knowledge, we are the first to investigate LLMs as evaluators on both closed-source and open-source models in the opinion summarization domain.

cs.CL↗

arXiv2024

Influential Billboard Slot Selection under Zonal Influence Constraint

Given billboard and trajectory database, finding a limited number of billboard slots for maximizing the influence is an important problem in the context of billboard advertisement. Most of the existing literature focused on the influential slot selection problem without considering any specific zonal influence constraint. To bridge this gap in this paper, we introduce and study the Influential Billboard Slot Selection Problem Under Zonal Influence Constraint. We propose a simple greedy approach to solve this problem. Though this method is easy to understand and simple to implement due to the excessive number of marginal gain computations, this method is not scalable. We design a branch and bound framework with two bound estimation techniques that divide the problem into different zones and integrate the zone-specific solutions to obtain a solution for the whole. We implement both the solution methodologies with real-world billboard and trajectory datasets and several experiments have been reported. We compare the performance of the proposed solution approaches with several baseline methods. The results show that the proposed approaches lead to more effective solutions with reasonable computational overhead than the baseline methods.

cs.DB↗

arXiv2024

Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarization

Reinforcement Learning from Human Feedback (RLHF) has become a dominating strategy in aligning Language Models (LMs) with human values/goals. The key to the strategy is learning a reward model ($φ$), which can reflect the latent reward model of humans. While this strategy has proven effective, the training methodology requires a lot of human preference annotation (usually in the order of tens of thousands) to train $φ$. Such a large-scale annotation is justifiable when it's a one-time effort, and the reward model is universally applicable. However, human goals are subjective and depend on the task, requiring task-specific preference annotations, which can be impractical to fulfill. To address this challenge, we propose a novel approach to infuse domain knowledge into $φ$, which reduces the amount of preference annotation required ($21\times$), omits Alignment Tax, and provides some interpretability. We validate our approach in E-Commerce Opinion Summarization, with a significant reduction in dataset size (to just $940$ samples) while advancing the SOTA ($\sim4$ point ROUGE-L improvement, $68\%$ of times preferred by humans over SOTA). Our contributions include a novel Reward Modeling technique and two new datasets: PromptOpinSumm (supervised data for Opinion Summarization) and OpinPref (a gold-standard human preference dataset). The proposed methodology opens up avenues for efficient RLHF, making it more adaptable to applications with varying human values. We release the artifacts (Code: github.com/efficient-rlhf. PromptOpinSumm: hf.co/prompt-opin-summ. OpinPref: hf.co/opin-pref) for usage under MIT License.

cs.CL↗

arXiv2024

Product Description and QA Assisted Self-Supervised Opinion Summarization

In e-commerce, opinion summarization is the process of summarizing the consensus opinions found in product reviews. However, the potential of additional sources such as product description and question-answers (QA) has been considered less often. Moreover, the absence of any supervised training data makes this task challenging. To address this, we propose a novel synthetic dataset creation (SDC) strategy that leverages information from reviews as well as additional sources for selecting one of the reviews as a pseudo-summary to enable supervised training. Our Multi-Encoder Decoder framework for Opinion Summarization (MEDOS) employs a separate encoder for each source, enabling effective selection of information while generating the summary. For evaluation, due to the unavailability of test sets with additional sources, we extend the Amazon, Oposum+, and Flipkart test sets and leverage ChatGPT to annotate summaries. Experiments across nine test sets demonstrate that the combination of our SDC approach and MEDOS model achieves on average a 14.5% improvement in ROUGE-1 F1 over the SOTA. Moreover, comparative analysis underlines the significance of incorporating additional sources for generating more informative summaries. Human evaluations further indicate that MEDOS scores relatively higher in coherence and fluency with 0.41 and 0.5 (-1 to 1) respectively, compared to existing models. To the best of our knowledge, we are the first to generate opinion summaries leveraging additional sources in a self-supervised setting.

cs.CL↗