Voucher Abuse Detection with Prompt-based Fine-tuning on Graph Neural Networks

Voucher abuse detection is an important anomaly detection problem in E-commerce. While many GNN-based solutions have emerged, the supervised paradigm depends on a large quantity of labeled data. A popular alternative is to adopt self-supervised pre-training using label-free data, and further fine-tune on a downstream task with limited labels. Nevertheless, the "pre-train, fine-tune" paradigm is often plagued by the objective gap between pre-training and downstream tasks. Hence, we propose VPGNN, a prompt-based fine-tuning framework on GNNs for voucher abuse detection. We design a novel graph prompting function to reformulate the downstream task into a similar template as the pretext task in pre-training, thereby narrowing the objective gap. Extensive experiments on both proprietary and public datasets demonstrate the strength of VPGNN in both few-shot and semi-supervised scenarios. Moreover, an online deployment of VPGNN in a production environment shows a 23.4% improvement over two existing deployed models.

Robust Long-Tailed Learning via Label-Aware Bounded CVaR

Data in the real-world classification problems are always imbalanced or long-tailed, wherein the majority classes have the most of the samples that dominate the model training. In such setting, the naive model tends to have poor performance on the minority classes. Previously, a variety of loss modifications have been proposed to address the long-tailed leaning problem, while these methods either treat the samples in the same class indiscriminatingly or lack a theoretical guarantee. In this paper, we propose two novel approaches based on CVaR (Conditional Value at Risk) to improve the performance of long-tailed learning with a solid theoretical ground. Specifically, we firstly introduce a Label-Aware Bounded CVaR (LAB-CVaR) loss to overcome the pessimistic result of the original CVaR, and further design the optimal weight bounds for LAB-CVaR theoretically. Based on LAB-CVaR, we additionally propose a LAB-CVaR with logit adjustment (LAB-CVaR-logit) loss to stabilize the optimization process, where we also offer the theoretical support. Extensive experiments on real-world datasets with long-tailed label distributions verify the superiority of our proposed methods.

Training-Free Energy Beamforming Assisted by Wireless Sensing

This paper studies the transmit energy beamforming in a multi-antenna wireless power transfer (WPT) system, in which an access point (AP) equipped with a uniform linear array (ULA) sends radio signals to wirelessly charge multiple single-antenna energy receivers (ERs). Different from conventional energy beamforming designs that require the AP to acquire the channel state information (CSI) via training and feedback, we propose a new training-free energy beamforming approach assisted by wireless radar sensing, which is implemented based on the following two-stage protocol. In the first stage, the AP performs wireless radar sensing to estimate the path gain and angle parameters of the ERs for constructing the corresponding CSI. In the second stage, the AP implements the transmit energy beamforming based on the constructed CSI to efficiently charge these ERs in a fair manner. Under this setup, first, we jointly optimize the sensing beamformers and duration in the first stage to minimize the sensing duration, while ensuring a given accuracy threshold for parameters estimation subject to the maximum transmit power constraint at the AP. Next, we optimize the energy beamformers in the second stage to maximize the minimum harvested energy by all ERs. In this approach, the estimation accuracy threshold for the first stage is properly designed to balance the resource allocation between the two stages for optimizing the ultimate energy harvesting performance. Finally, numerical results show that the proposed training-free energy beamforming design performs close to the performance upper bound with perfect CSI, and outperforms the benchmark schemes without such joint optimization and that with isotropic transmission.

OmniDataComposer: A Unified Data Structure for Multimodal Data Fusion and Infinite Data Generation

This paper presents OmniDataComposer, an innovative approach for multimodal data fusion and unlimited data generation with an intent to refine and uncomplicate interplay among diverse data modalities. Coming to the core breakthrough, it introduces a cohesive data structure proficient in processing and merging multimodal data inputs, which include video, audio, and text. Our crafted algorithm leverages advancements across multiple operations such as video/image caption extraction, dense caption extraction, Automatic Speech Recognition (ASR), Optical Character Recognition (OCR), Recognize Anything Model(RAM), and object tracking. OmniDataComposer is capable of identifying over 6400 categories of objects, substantially broadening the spectrum of visual information. It amalgamates these diverse modalities, promoting reciprocal enhancement among modalities and facilitating cross-modal data correction. \textbf{The final output metamorphoses each video input into an elaborate sequential document}, virtually transmuting videos into thorough narratives, making them easier to be processed by large language models. Future prospects include optimizing datasets for each modality to encourage unlimited data generation. This robust base will offer priceless insights to models like ChatGPT, enabling them to create higher quality datasets for video captioning and easing question-answering tasks based on video content. OmniDataComposer inaugurates a new stage in multimodal learning, imparting enormous potential for augmenting AI's understanding and generation of complex, real-world data.

Fundamental CRB-Rate Tradeoff in Multi-Antenna ISAC Systems with Information Multicasting and Multi-Target Sensing

This paper investigates the performance tradeoff for a multi-antenna integrated sensing and communication (ISAC) system with simultaneous information multicasting and multi-target sensing, in which a multi-antenna base station (BS) sends the common information messages to a set of single-antenna communication users (CUs) and estimates the parameters of multiple sensing targets based on the echo signals concurrently. We consider two target sensing scenarios without and with prior target knowledge at the BS, in which the BS is interested in estimating the complete multi-target response matrix and the target reflection coefficients/angles, respectively. First, we consider the capacity-achieving transmission and characterize the fundamental tradeoff between the achievable rate and the multi-target estimation Cram\'er-Rao bound (CRB) accordingly.

Prompt Tuning on Graph-augmented Low-resource Text Classification

Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with no or few labeled samples, presents a serious concern for supervised learning. Meanwhile, many text data are inherently grounded on a network structure, such as a hyperlink/citation network for online articles, and a user-item purchase network for e-commerce products. These graph structures capture rich semantic relationships, which can potentially augment low-resource text classification. In this paper, we propose a novel model called Graph-Grounded Pre-training and Prompting (G2P2) to address low-resource text classification in a two-pronged approach. During pre-training, we propose three graph interaction-based contrastive strategies to jointly pre-train a graph-text model; during downstream classification, we explore handcrafted discrete prompts and continuous prompt tuning for the jointly pre-trained model to achieve zero- and few-shot classification, respectively. Besides, for generalizing continuous prompts to unseen classes, we propose conditional prompt tuning on graphs (G2P2$^*$). Extensive experiments on four real-world datasets demonstrate the strength of G2P2 in zero- and few-shot low-resource text classification tasks, and illustrate the advantage of G2P2$^*$ in dealing with unseen classes.

Optimal Coordinated Transmit Beamforming for Networked Integrated Sensing and Communications

This paper studies a multi-antenna networked integrated sensing and communications (ISAC) system, in which a set of multi-antenna base stations (BSs) employ the coordinated transmit beamforming to serve multiple single-antenna communication users (CUs) and perform joint target detection by exploiting the reflected signals simultaneously. To facilitate target sensing, the BSs transmit dedicated sensing signals combined with their information signals. Accordingly, we consider two types of CU receivers with and without the capability of canceling the interference from the dedicated sensing signals, respectively. In addition, we investigate two scenarios with and without time synchronization among the BSs. For the scenario with synchronization, the BSs can exploit the target-reflected signals over both the direct links (BS-to-target-to-originated BS links) and the cross-links (BS-to-target-to-other BSs links) for joint detection, while in the unsynchronized scenario, the BSs can only utilize the target-reflected signals over the direct links. For each scenario under different types of CU receivers, we optimize the coordinated transmit beamforming at the BSs to maximize the minimum detection probability over a particular targeted area, while guaranteeing the required minimum signal-to-interference-plus-noise ratio (SINR) constraints at the CUs. These SINR-constrained detection probability maximization problems are recast as non-convex quadratically constrained quadratic programs (QCQPs), which are then optimally solved via the semi-definite relaxation (SDR) technique.

Multi-IRS-Enabled Integrated Sensing and Communications

This paper studies a multi-intelligent-reflecting-surface-(IRS)-enabled integrated sensing and communications (ISAC) system, in which multiple IRSs are installed to help the base station (BS) provide ISAC services at separate line-of-sight (LoS) blocked areas. We focus on the scenario with semi-passive uniform linear array (ULA) IRSsfor sensing, in which each IRS is integrated with dedicated sensors for processing echo signals, and each IRS simultaneously serves one sensing target and one communication user (CU) in its coverage area. In particular, we suppose that the BS sends combined information and dedicated sensing signals for ISAC, and we consider two cases with point and extended targets, in which each IRS aims to estimate the direction-of-arrival (DoA) of the corresponding target and the complete target response matrix, respectively. Under this setup, we first derive the closed-form Cram{\'e}r-Rao bounds (CRBs) for parameters estimation under the two target models. For the point target case, the CRB for AoA estimation is shown to be inversely proportional to the cubic of the number of sensors at each IRS, while for the extended target case, the CRB for target response matrix estimation is proportional to the number of IRS sensors. Next, we consider two different types of CU receivers that can and cannot cancel the interference from dedicated sensing signals prior to information decoding. To achieve fair and optimized sensing performance, we minimize the maximum CRB at all IRSs for the two target cases, via jointly optimizing the transmit beamformers at the BS and the reflective beamformers at the multiple IRSs, subject to the minimum signal-to-interference-plus-noise ratio (SINR) constraints at individual CUs, the maximum transmit power constraint at the BS, and the unit-modulus constraints at the multiple IRSs.