Search

Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since covered extensive areas of traditional learning tasks. For instance, text-based tasks such as text-classification and sequence-labeling, as well as multi-modal tasks like Visual Question Answering (VQA) and Optical Character Recognition (OCR), which were previously addressed using different models, can now be tackled based on one foundation model. Consequently, the training and lightweight fine-tuning of LLMs and MLLMs, especially those based on Transformer architecture, has become particularly important. In recognition of these overwhelming needs, we develop SWIFT, a customizable one-stop infrastructure for large models. With support of over $300+$ LLMs and $50+$ MLLMs, SWIFT stands as the open-source framework that provide the most comprehensive support for fine-tuning large models. In particular, it is the first training framework that provides systematic support for MLLMs. In addition to the core functionalities of fine-tuning, SWIFT also integrates post-training processes such as inference, evaluation, and model quantization, to facilitate fast adoptions of large models in various application scenarios. With a systematic integration of various training techniques, SWIFT offers helpful utilities such as benchmark comparisons among different training techniques for large models. For fine-tuning models specialized in agent framework, we show that notable improvements on the ToolBench leader-board can be achieved by training with customized dataset on SWIFT, with an increase of 5.2%-21.8% in the Act.EM metric over various baseline models, a reduction in hallucination by 1.6%-14.1%, and an average performance improvement of 8%-17%.

Designing effective data manipulation methods is a long standing problem in data lakes. Traditional methods, which rely on rules or machine learning models, require extensive human efforts on training data collection and tuning models. Recent methods apply Large Language Models (LLMs) to resolve multiple data manipulation tasks. They exhibit bright benefits in terms of performance but still require customized designs to fit each specific task. This is very costly and can not catch up with the requirements of big data lake platforms. In this paper, inspired by the cross-task generality of LLMs on NLP tasks, we pave the first step to design an automatic and general solution to tackle with data manipulation tasks. We propose UniDM, a unified framework which establishes a new paradigm to process data manipulation tasks using LLMs. UniDM formalizes a number of data manipulation tasks in a unified form and abstracts three main general steps to solve each task. We develop an automatic context retrieval to allow the LLMs to retrieve data from data lakes, potentially containing evidence and factual information. For each step, we design effective prompts to guide LLMs to produce high quality results. By our comprehensive evaluation on a variety of benchmarks, our UniDM exhibits great generality and state-of-the-art performance on a wide variety of data manipulation tasks., Comment: MLSys24

Partial Label Learning (PLL) tackles model learning from the data with inexact labels under the assumption that training and test objects are in the same distribution, i.e., closed-set scenario. Nevertheless, this assumption does not hold in real-world open-set scenarios where test data may come from Out-Of-Distribution (OOD), resulting in object detection failure and hence significantly compromising the PLL model's security and trustworthiness. This is a previously unexplored problem called Out-Of-Distribution Partial Label Learning (OODPLL) that our newly proposed PLOOD framework can effectively resolve. During the training phase, our framework leverages self-supervised learning strategy to generate positive and negative samples for each object, emulating in and out-of-distributions respectively. Under these distributions, PLL methods can learn discriminative features for OOD objects. In the inference phase, a novel Partial Energy (PE) scoring technique is proposed which leverages the label confidence established during the above training phase to mine the actual labels. In this way, the issue of inexact labeling in PLL can be effectively addressed for significantly better performance in OOD object detection. PLOOD is compared with SOTA PLL models and OOD scores on CIFAR-10 and CIFAR-100 datasets against various OOD datasets. The results demonstrate the effectiveness of our PLOOD framework, significantly outperforming SOTA PLL models and marking a substantial advancement in addressing PLL problems in real-world OOD scenarios.

Instruction tuning has been identified as a crucial technique for optimizing the performance of large language models (LLMs) in generating human-aligned responses. Nonetheless, gathering diversified and superior-quality instruction data for such tuning presents notable obstacles, especially in domains with rigid privacy provisions. Federated instruction tuning (FedIT) has emerged as a promising solution, by consolidating collaborative training across multiple data owners, thereby resulting in a privacy-preserving learning model. However, FedIT encounters limitations such as scarcity of instructional data and risk of exposure to training data extraction attacks. In this paper, we propose a novel federated algorithm, FewFedPIT, designed to simultaneously enhance privacy protection and model performance of federated few-shot learning. FewFedPITcomprises three vital components on the client side: (1) synthetic data generation, which utilizes LLMs' in-context learning capacity to generate synthetic data autonomously, thus expanding the local database; (2) parameter isolation training, which individually updates the public parameters in the synthetic data and the private parameters in the local data, consequently mitigating the noise impact of the synthetic data; (3) local aggregation sharing, which mixes public and private parameters before uploading, effectively preventing data extraction attacks. Extensive experiments on three open-source datasets demonstrate the effectiveness of FewFedPITin, enhancing privacy preservation and improving federated few-shot performance., Comment: Work in progress

Non-fungible tokens (NFTs) drive the prosperity of the Web3 ecosystem. By November 2023, the total market value of NFT projects reached approximately 16 billion USD. Accompanying the success of NFTs are various security issues, i.e., attacks and scams are prevalent in the ecosystem. While NFTs have attracted significant attentions from both industry and academia, there is a lack of understanding of kinds of NFT security issues. The discovery, in-depth analysis, and systematic categorization of these security issues are of significant importance for the prosperous development of the NFT ecosystem. To fill the gap, we performed a systematic literature review related to NFT security, and we have identified 142 incidents from 213 security reports and 18 academic papers until October 1st, 2023. Through manual analysis of the compiled security incidents, we have classified them into 12 major categories. Then we explored potential solutions and mitigation strategies. Drawing from these analyses, we established the first NFT security reference frame. Except, we extracted the characteristics of NFT security issues, i.e., the prevalence, severity, and intractability. We have indicated the gap between industry and academy for NFT security, and provide further research directions for the community. This paper, as the first SoK of NFT security, has systematically explored the security issues within the NFT ecosystem, shedding light on their root causes, real-world attacks, and potential ways to address them. Our findings will contribute to the future research of NFT security.

Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients. But meanwhile, the distributed and isolated nature of data isolation may be complicated by data quality, making it more vulnerable to noisy labels. Many efforts exist to defend against the negative impacts of noisy labels in centralized or federated settings. However, there is a lack of a benchmark that comprehensively considers the impact of noisy labels in a wide variety of typical FL settings. In this work, we serve the first standardized benchmark that can help researchers fully explore potential federated noisy settings. Also, we conduct comprehensive experiments to explore the characteristics of these data settings and unravel challenging scenarios on the federated noisy label learning, which may guide method development in the future. We highlight the 20 basic settings for more than 5 datasets proposed in our benchmark and standardized simulation pipeline for federated noisy label learning. We hope this benchmark can facilitate idea verification in federated learning with noisy labels. \texttt{FedNoisy} is available at \codeword{https://github.com/SMILELab-FL/FedNoisy}., Comment: Update appendix experiment results

NFT rug pull is one of the most prominent type of scam that the developers of a project abandon it and then run away with investors' funds. Although they have drawn attention from our community, to the best of our knowledge, the NFT rug pulls have not been systematically explored. To fill the void, this paper presents the first in-depth study of NFT rug pulls. Specifically, we first compile a list of 253 known NFT rug pulls as our initial ground truth, based on which we perform a pilot study, highlighting the key symptoms of NFT rug pulls. Then, we enforce a strict rule-based method to flag more rug pulled NFT projects in the wild, and have labelled 7,487 NFT rug pulls as our extended ground truth. Atop it, we have investigated the art of NFT rug pulls, with kinds of tricks including explicit ones that are embedded with backdoors, and implicit ones that manipulate the market. To release the expansion of the scam, we further design a prediction model to proactively identify the potential rug pull projects in an early stage ahead of the scam happens. We have implemented a prototype system deployed in the real-world setting for over 5 months. Our system has raised alarms for 7,821 NFT projects, by the time of this writing, which can work as a whistle blower that pinpoints rug pull scams timely, thus mitigating the impacts.

Multi-instance multi-label (MIML) learning is widely applicated in numerous domains, such as the image classification where one image contains multiple instances correlated with multiple logic labels simultaneously. The related labels in existing MIML are all assumed as logical labels with equal significance. However, in practical applications in MIML, significance of each label for multiple instances per bag (such as an image) is significant different. Ignoring labeling significance will greatly lose the semantic information of the object, so that MIML is not applicable in complex scenes with a poor learning performance. To this end, this paper proposed a novel MIML framework based on graph label enhancement, namely GLEMIML, to improve the classification performance of MIML by leveraging label significance. GLEMIML first recognizes the correlations among instances by establishing the graph and then migrates the implicit information mined from the feature space to the label space via nonlinear mapping, thus recovering the label significance. Finally, GLEMIML is trained on the enhanced data through matching and interaction mechanisms. GLEMIML (AvgRank: 1.44) can effectively improve the performance of MIML by mining the label distribution mechanism and show better results than the SOTA method (AvgRank: 2.92) on multiple benchmark datasets., Comment: 7 pages,2 figures