Towards Effective Data-Free Knowledge Distillation via Diverse Diffusion Augmentation

Data-free knowledge distillation (DFKD) has emerged as a pivotal technique in the domain of model compression, substantially reducing the dependency on the original training data. Nonetheless, conventional DFKD methods that employ synthesized training data are prone to the limitations of inadequate diversity and discrepancies in distribution between the synthesized and original datasets. To address these challenges, this paper introduces an innovative approach to DFKD through diverse diffusion augmentation (DDA). Specifically, we revise the paradigm of common data synthesis in DFKD to a composite process through leveraging diffusion models subsequent to data synthesis for self-supervised augmentation, which generates a spectrum of data samples with similar distributions while retaining controlled variations. Furthermore, to mitigate excessive deviation in the embedding space, we introduce an image filtering technique grounded in cosine similarity to maintain fidelity during the knowledge distillation process. Comprehensive experiments conducted on CIFAR-10, CIFAR-100, and Tiny-ImageNet datasets showcase the superior performance of our method across various teacher-student network configurations, outperforming the contemporary state-of-the-art DFKD methods. Code will be available at:https://github.com/SLGSP/DDA.

MuAP: Multi-step Adaptive Prompt Learning for Vision-Language Model with Missing Modality

Recently, prompt learning has garnered considerable attention for its success in various Vision-Language (VL) tasks. However, existing prompt-based models are primarily focused on studying prompt generation and prompt strategies with complete modality settings, which does not accurately reflect real-world scenarios where partial modality information may be missing. In this paper, we present the first comprehensive investigation into prompt learning behavior when modalities are incomplete, revealing the high sensitivity of prompt-based models to missing modalities. To this end, we propose a novel Multi-step Adaptive Prompt Learning (MuAP) framework, aiming to generate multimodal prompts and perform multi-step prompt tuning, which adaptively learns knowledge by iteratively aligning modalities. Specifically, we generate multimodal prompts for each modality and devise prompt strategies to integrate them into the Transformer model. Subsequently, we sequentially perform prompt tuning from single-stage and alignment-stage, allowing each modality-prompt to be autonomously and adaptively learned, thereby mitigating the imbalance issue caused by only textual prompts that are learnable in previous works. Extensive experiments demonstrate the effectiveness of our MuAP and this model achieves significant improvements compared to the state-of-the-art on all benchmark datasets

No Language is an Island: Unifying Chinese and English in Financial Large Language Models, Instruction Data, and Benchmarks

While the progression of Large Language Models (LLMs) has notably propelled financial analysis, their application has largely been confined to singular language realms, leaving untapped the potential of bilingual Chinese-English capacity. To bridge this chasm, we introduce ICE-PIXIU, seamlessly amalgamating the ICE-INTENT model and ICE-FLARE benchmark for bilingual financial analysis. ICE-PIXIU uniquely integrates a spectrum of Chinese tasks, alongside translated and original English datasets, enriching the breadth and depth of bilingual financial modeling. It provides unrestricted access to diverse model variants, a substantial compilation of diverse cross-lingual and multi-modal instruction data, and an evaluation benchmark with expert annotations, comprising 10 NLP tasks, 20 bilingual specific tasks, totaling 1,185k datasets. Our thorough evaluation emphasizes the advantages of incorporating these bilingual datasets, especially in translation tasks and utilizing original English data, enhancing both linguistic flexibility and analytical acuity in financial contexts. Notably, ICE-INTENT distinguishes itself by showcasing significant enhancements over conventional LLMs and existing financial LLMs in bilingual milieus, underscoring the profound impact of robust bilingual data on the accuracy and efficacy of financial NLP.

Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learning

Scene graph generation (SGG) endeavors to predict visual relationships between pairs of objects within an image. Prevailing SGG methods traditionally assume a one-off learning process for SGG. This conventional paradigm may necessitate repetitive training on all previously observed samples whenever new relationships emerge, mitigating the risk of forgetting previously acquired knowledge. This work seeks to address this pitfall inherent in a suite of prior relationship predictions. Motivated by the achievements of in-context learning in pretrained language models, our approach imbues the model with the capability to predict relationships and continuously acquire novel knowledge without succumbing to catastrophic forgetting. To achieve this goal, we introduce a novel and pragmatic framework for scene graph generation, namely Lifelong Scene Graph Generation (LSGG), where tasks, such as predicates, unfold in a streaming fashion. In this framework, the model is constrained to exclusive training on the present task, devoid of access to previously encountered training data, except for a limited number of exemplars, but the model is tasked with inferring all predicates it has encountered thus far. Rigorous experiments demonstrate the superiority of our proposed method over state-of-the-art SGG models in the context of LSGG across a diverse array of metrics. Besides, extensive experiments on the two mainstream benchmark datasets, VG and Open-Image(v6), show the superiority of our proposed model to a number of competitive SGG models in terms of continuous learning and conventional settings. Moreover, comprehensive ablation experiments demonstrate the effectiveness of each component in our model.

Graph Entropy Minimization for Semi-supervised Node Classification

Node classifiers are required to comprehensively reduce prediction errors, training resources, and inference latency in the industry. However, most graph neural networks (GNN) concentrate only on one or two of them. The compromised aspects thus are the shortest boards on the bucket, hindering their practical deployments for industrial-level tasks. This work proposes a novel semi-supervised learning method termed Graph Entropy Minimization (GEM) to resolve the three issues simultaneously. GEM benefits its one-hop aggregation from massive uncategorized nodes, making its prediction accuracy comparable to GNNs with two or more hops message passing. It can be decomposed to support stochastic training with mini-batches of independent edge samples, achieving extremely fast sampling and space-saving training. While its one-hop aggregation is faster in inference than deep GNNs, GEM can be further accelerated to an extreme by deriving a non-hop classifier via online knowledge distillation. Thus, GEM can be a handy choice for latency-restricted and error-sensitive services running on resource-constraint hardware. Code is available at https://github.com/cf020031308/GEM.

VQA and Visual Reasoning: An Overview of Recent Datasets, Methods and Challenges

Artificial Intelligence (AI) and its applications have sparked extraordinary interest in recent years. This achievement can be ascribed in part to advances in AI subfields including Machine Learning (ML), Computer Vision (CV), and Natural Language Processing (NLP). Deep learning, a sub-field of machine learning that employs artificial neural network concepts, has enabled the most rapid growth in these domains. The integration of vision and language has sparked a lot of attention as a result of this. The tasks have been created in such a way that they properly exemplify the concepts of deep learning. In this review paper, we provide a thorough and an extensive review of the state of the arts approaches, key models design principles and discuss existing datasets, methods, their problem formulation and evaluation measures for VQA and Visual reasoning tasks to understand vision and language representation learning. We also present some potential future paths in this field of research, with the hope that our study may generate new ideas and novel approaches to handle existing difficulties and develop new applications.

QuatDE: Dynamic Quaternion Embedding for Knowledge Graph Completion

In recent years, knowledge graph completion methods have been extensively studied, in which graph embedding approaches learn low dimensional representations of entities and relations to predict missing facts. Those models usually view the relation vector as a translation (TransE) or rotation (rotatE and QuatE) between entity pairs, enjoying the advantage of simplicity and efficiency. However, QuatE has two main problems: 1) The model to capture the ability of representation and feature interaction between entities and relations are relatively weak because it only relies on the rigorous calculation of three embedding vectors; 2) Although the model can handle various relation patterns including symmetry, anti-symmetry, inversion and composition, but mapping properties of relations are not to be considered, such as one-to-many, many-to-one, and many-to-many. In this paper, we propose a novel model, QuatDE, with a dynamic mapping strategy to explicitly capture a variety of relational patterns, enhancing the feature interaction capability between elements of the triplet. Our model relies on three extra vectors donated as subject transfer vector, object transfer vector and relation transfer vector. The mapping strategy dynamically selects the transition vectors associated with each triplet, used to adjust the point position of the entity embedding vectors in the quaternion space via Hamilton product. Experiment results show QuatDE achieves state-of-the-art performance on three well-established knowledge graph completion benchmarks. In particular, the MR evaluation has relatively increased by 26% on WN18 and 15% on WN18RR, which proves the generalization of QuatDE.

Deep Neural Network Based Relation Extraction: An Overview

Knowledge is a formal way of understanding the world, providing a human-level cognition and intelligence for the next-generation artificial intelligence (AI). One of the representations of knowledge is semantic relations between entities. An effective way to automatically acquire this important knowledge, called Relation Extraction (RE), a sub-task of information extraction, plays a vital role in Natural Language Processing (NLP). Its purpose is to identify semantic relations between entities from natural language text. To date, there are several studies for RE in previous works, which have documented these techniques based on Deep Neural Networks (DNNs) become a prevailing technique in this research. Especially, the supervised and distant supervision methods based on DNNs are the most popular and reliable solutions for RE. This article 1) introduces some general concepts, and further 2) gives a comprehensive overview of DNNs in RE from two points of view: supervised RE, which attempts to improve the standard RE systems, and distant supervision RE, which adopts DNNs to design sentence encoder and de-noise method. We further 3) cover some novel methods and recent trends as well as discuss possible future research directions for this task.

Sparse Label Smoothing for Semi-supervised Person Re-Identification

Person re-identification (re-id) is a cross-camera retrieval task which establishes a correspondence between images of a person from multiple cameras. Deep Learning methods have been successfully applied to the problem and achieved impressive results. However, these methods require large amounts of labeled training data. Current labeled datasets in person re-id are limited in scale and manually acquiring such large-scale dataset in surveillance camera is a tedious and labor-intensive task. In this paper, we propose a semi-supervised framework that performs Sparse Label Smoothing Regularization (SLSR) by considering similarities between unlabeled sample and training sample in the same feature space. Our approach first exploits the clustering property of existing person re-id datasets to create groups of similar objects that model the correlation among view. We make use of the training set to create cluster of similar objects using the intermediate feature representation of a CNN model. Each cluster is used to generate synthetic data samples using a generative adversarial model. We finally defined a sparse smoothing regularization term and train the network with join supervision of cross-entropy loss. The proposed approach tackles two problems (1) how to efficiently use the generated data and (2) how to address the over-smoothness problem found in current regularization. We solve these two problems by using a generative model for data augmentation and by maintaining and propagating similarities across the network through the concatenation of training images and generated images into one homogeneous feature space. Extensive experiments on four large-scale datasets show that our regularization method significantly improves the Re-ID accuracy compared to existing semi-supervised methods.

Self Attention Grid for Person Re-Identification

In this paper, we present an attention mechanism scheme to improve person re-identification task. Inspired by biology, we propose Self Attention Grid (SAG) to discover the most informative parts from a high-resolution image using its internal representation. In particular, given an input image, the proposed model is fed with two copies of the same image and consists of two branches. The upper branch processes the high-resolution image and learns high dimensional feature representation while the lower branch processes the low-resolution image and learn a filtering attention grid. We apply a max filter operation to non-overlapping sub-regions on the high feature representation before element-wise multiplied with the output of the second branch. The feature maps of the second branch are subsequently weighted to reflect the importance of each patch of the grid using a softmax operation. Our attention module helps the network learn the most discriminative visual features of multiple image regions and is specifically optimized to attend feature representation at different levels. Extensive experiments on three large-scale datasets show that our self-attention mechanism significantly improves the baseline model and outperforms various state-of-art models by a large margin.