In recent years, Wi-Fi sensing has garnered significant attention due to its numerous benefits, such as privacy protection, low cost, and penetration ability. Extensive research has been conducted in this field, focusing on areas such as gesture recognition, people identification, and fall detection. However, many data-driven methods encounter challenges related to domain shift, where the model fails to perform well in environments different from the training data. One major factor contributing to this issue is the limited availability of Wi-Fi sensing datasets, which makes models learn excessive irrelevant information and over-fit to the training set. Unfortunately, collecting large-scale Wi-Fi sensing datasets across diverse scenarios is a challenging task. To address this problem, we propose CrossFi, a siamese network-based approach that excels in both in-domain scenario and cross-domain scenario, including few-shot, zero-shot scenarios, and even works in few-shot new-class scenario where testing set contains new categories. The core component of CrossFi is a sample-similarity calculation network called CSi-Net, which improves the structure of the siamese network by using an attention mechanism to capture similarity information, instead of simply calculating the distance or cosine similarity. Based on it, we develop an extra Weight-Net that can generate a template for each class, so that our CrossFi can work in different scenarios. Experimental results demonstrate that our CrossFi achieves state-of-the-art performance across various scenarios. In gesture recognition task, our CrossFi achieves an accuracy of 98.17% in in-domain scenario, 91.72% in one-shot cross-domain scenario, 64.81% in zero-shot cross-domain scenario, and 84.75% in one-shot new-class scenario. To facilitate future research, we will release the code for our model upon publication.
相關內容
To handle the vast amounts of qualitative data produced in corporate climate communication, stakeholders increasingly rely on Retrieval Augmented Generation (RAG) systems. However, a significant gap remains in evaluating domain-specific information retrieval - the basis for answer generation. To address this challenge, this work simulates the typical tasks of a sustainability analyst by examining 30 sustainability reports with 16 detailed climate-related questions. As a result, we obtain a dataset with over 8.5K unique question-source-answer pairs labeled by different levels of relevance. Furthermore, we develop a use case with the dataset to investigate the integration of expert knowledge into information retrieval with embeddings. Although we show that incorporating expert knowledge works, we also outline the critical limitations of embeddings in knowledge-intensive downstream domains like climate change communication.
Text-to-SQL technology has become crucial for translating natural language into SQL queries in various industries, enabling non-technical users to perform complex data operations. The need for accurate evaluation methods has increased as these systems have grown more sophisticated. However, we found that the Execution Accuracy (EX), the most promising evaluation metric, still shows a substantial portion of false positives and negatives compared to human evaluation. Thus, this paper introduces FLEX (False-Less EXecution), a novel approach to evaluating text-to-SQL systems using large language models (LLMs) to emulate human expert-level evaluation of SQL queries. Our method shows significantly higher agreement with human expert judgments, improving Cohen's kappa from 61 to 78.17. Re-evaluating top-performing models on the Spider and BIRD benchmarks using FLEX reveals substantial shifts in performance rankings, with an average performance decrease of 3.15 due to false positive corrections and an increase of 6.07 from addressing false negatives. This work contributes to a more accurate and nuanced evaluation of text-to-SQL systems, potentially reshaping our understanding of state-of-the-art performance in this field.
The impressive performance of Large Language Models (LLMs) has consistently surpassed numerous human-designed benchmarks, presenting new challenges in assessing the shortcomings of LLMs. Designing tasks and finding LLMs' limitations are becoming increasingly important. In this paper, we investigate the question of whether an LLM can discover its own limitations from the errors it makes. To this end, we propose a Self-Challenge evaluation framework with human-in-the-loop. Starting from seed instances that GPT-4 fails to answer, we prompt GPT-4 to summarize error patterns that can be used to generate new instances and incorporate human feedback on them to refine these patterns for generating more challenging data, iteratively. We end up with 8 diverse patterns, such as text manipulation and questions with assumptions. We then build a benchmark, SC-G4, consisting of 1,835 instances generated by GPT-4 using these patterns, with human-annotated gold responses. The SC-G4 serves as a challenging benchmark that allows for a detailed assessment of LLMs' abilities. Our results show that only 44.96\% of instances in SC-G4 can be answered correctly by GPT-4. Interestingly, our pilot study indicates that these error patterns also challenge other LLMs, such as Claude-3 and Llama-3, and cannot be fully resolved through fine-tuning. Our work takes the first step to demonstrate that LLMs can autonomously identify their inherent flaws and provide insights for future dynamic and automatic evaluation.
This paper addresses the critical task of gait cycle segmentation using short sequences from ear-worn IMUs, a practical and non-invasive approach for home-based monitoring and rehabilitation of patients with impaired motor function. While previous studies have focused on IMUs positioned on the lower limbs, ear-worn IMUs offer a unique advantage in capturing gait dynamics with minimal intrusion. To address the challenges of gait cycle segmentation using short sequences, we introduce the Gait Characteristic Curve Regression and Restoration (GCCRR) method, a novel two-stage approach designed for fine-grained gait phase segmentation. The first stage transforms the segmentation task into a regression task on the Gait Characteristic Curve (GCC), which is a one-dimensional feature sequence incorporating periodic information. The second stage restores the gait cycle using peak detection techniques. Our method employs Bi-LSTM-based deep learning algorithms for regression to ensure reliable segmentation for short gait sequences. Evaluation on the HamlynGait dataset demonstrates that GCCRR achieves over 80\% Accuracy, with a Timestamp Error below one sampling interval. Despite its promising results, the performance lags behind methods using more extensive sensor systems, highlighting the need for larger, more diverse datasets. Future work will focus on data augmentation using motion capture systems and improving algorithmic generalizability.
In certain emerging applications such as health monitoring wearable and traffic monitoring systems, Internet-of-Things (IoT) devices generate or collect a huge amount of multi-label datasets. Within these datasets, each instance is linked to a set of labels. The presence of noisy, redundant, or irrelevant features in these datasets, along with the curse of dimensionality, poses challenges for multi-label classifiers. Feature selection (FS) proves to be an effective strategy in enhancing classifier performance and addressing these challenges. Yet, there is currently no existing distributed multi-label FS method documented in the literature that is suitable for distributed multi-label datasets within IoT environments. This paper introduces FMLFS, the first federated multi-label feature selection method. Here, mutual information between features and labels serves as the relevancy metric, while the correlation distance between features, derived from mutual information and joint entropy, is utilized as the redundancy measure. Following aggregation of these metrics on the edge server and employing Pareto-based bi-objective and crowding distance strategies, the sorted features are subsequently sent back to the IoT devices. The proposed method is evaluated through two scenarios: 1) transmitting reduced-size datasets to the edge server for centralized classifier usage, and 2) employing federated learning with reduced-size datasets. Evaluation across three metrics - performance, time complexity, and communication cost - demonstrates that FMLFS outperforms five other comparable methods in the literature and provides a good trade-off on three real-world datasets.
Existing evaluation benchmarks of language models of code (code LMs) focus almost exclusively on whether the LMs can generate functionally-correct code. In real-world software engineering, developers think beyond functional correctness. They have requirements on "how" a functionality should be implemented to meet overall system design objectives like efficiency, security, and maintainability. They would also trust the code LMs more if the LMs demonstrate robust understanding of such requirements. We propose a new benchmark NoFunEval to evaluate code LMs on non-functional requirements and simple classification instances for both functional and non-functional requirements. We propose a prompting method, Coding Concepts (CoCo), as a way for a developer to communicate the domain knowledge to the LMs. We conduct an extensive evaluation of 27 code LMs. Our finding is that LMs generally falter when tested on our benchmark, hinting at fundamental blindspots in their training setups. Surprisingly, even the classification accuracy on functional-correctness instances derived from the popular HumanEval benchmark is low, calling in question the depth of their comprehension and the source of their success in generating functionally-correct code in the first place. We release our benchmark and evaluation scripts publicly at //aka.ms/NoFunEval.
Large Language Models (LLMs) like GPT-4, LLaMA, and Qwen have demonstrated remarkable success across a wide range of applications. However, these models remain inherently vulnerable to prompt injection attacks, which can bypass existing safety mechanisms, highlighting the urgent need for more robust attack detection methods and comprehensive evaluation benchmarks. To address these challenges, we introduce GenTel-Safe, a unified framework that includes a novel prompt injection attack detection method, GenTel-Shield, along with a comprehensive evaluation benchmark, GenTel-Bench, which compromises 84812 prompt injection attacks, spanning 3 major categories and 28 security scenarios. To prove the effectiveness of GenTel-Shield, we evaluate it together with vanilla safety guardrails against the GenTel-Bench dataset. Empirically, GenTel-Shield can achieve state-of-the-art attack detection success rates, which reveals the critical weakness of existing safeguarding techniques against harmful prompts. For reproducibility, we have made the code and benchmarking dataset available on the project page at //gentellab.github.io/gentel-safe.github.io/.
The Software Supply Chain (SSC) has captured considerable attention from attackers seeking to infiltrate systems and undermine organizations. There is evidence indicating that adversaries utilize Social Engineering (SocE) techniques specifically aimed at software developers. That is, they interact with developers at critical steps in the Software Development Life Cycle (SDLC), such as accessing Github repositories, incorporating code dependencies, and obtaining approval for Pull Requests (PR) to introduce malicious code. This paper aims to comprehensively explore the existing and emerging SocE tactics employed by adversaries to trick Software Engineers (SWEs) into delivering malicious software. By analyzing a diverse range of resources, which encompass established academic literature and real-world incidents, the paper systematically presents an overview of these manipulative strategies within the realm of the SSC. Such insights prove highly beneficial for threat modeling and security gap analysis.
Climate change (CC) has attracted increasing attention in NLP in recent years. However, detecting the stance on CC in multimodal data is understudied and remains challenging due to a lack of reliable datasets. To improve the understanding of public opinions and communication strategies, this paper presents MultiClimate, the first open-source manually-annotated stance detection dataset with $100$ CC-related YouTube videos and $4,209$ frame-transcript pairs. We deploy state-of-the-art vision and language models, as well as multimodal models for MultiClimate stance detection. Results show that text-only BERT significantly outperforms image-only ResNet50 and ViT. Combining both modalities achieves state-of-the-art, $0.747$/$0.749$ in accuracy/F1. Our 100M-sized fusion models also beat CLIP and BLIP, as well as the much larger 9B-sized multimodal IDEFICS and text-only Llama3 and Gemma2, indicating that multimodal stance detection remains challenging for large language models. Our code, dataset, as well as supplementary materials, are available at //github.com/werywjw/MultiClimate.
Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems. In this paper, we consider knowledge graphs as the source of side information. We propose MKR, a Multi-task feature learning approach for Knowledge graph enhanced Recommendation. MKR is a deep end-to-end framework that utilizes knowledge graph embedding task to assist recommendation task. The two tasks are associated by cross&compress units, which automatically share latent features and learn high-order interactions between items in recommender systems and entities in the knowledge graph. We prove that cross&compress units have sufficient capability of polynomial approximation, and show that MKR is a generalized framework over several representative methods of recommender systems and multi-task learning. Through extensive experiments on real-world datasets, we demonstrate that MKR achieves substantial gains in movie, book, music, and news recommendation, over state-of-the-art baselines. MKR is also shown to be able to maintain a decent performance even if user-item interactions are sparse.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191