Training Costs Research Articles

GOODAT: Towards Test-Time Graph Out-of-Distribution Detection

Graph neural networks (GNNs) have found widespread application in modeling graph data across diverse domains. While GNNs excel in scenarios where the testing data shares the distribution of their training counterparts (in distribution, ID), they often exhibit incorrect predictions when confronted with samples from an unfamiliar distribution (out-of-distribution, OOD). To identify and reject OOD samples with GNNs, recent studies have explored graph OOD detection, often focusing on training a specific model or modifying the data on top of a well-trained GNN. Despite their effectiveness, these methods come with heavy training resources and costs, as they need to optimize the GNN-based models on training data. Moreover, their reliance on modifying the original GNNs and accessing training data further restricts their universality. To this end, this paper introduces a method to detect Graph Out-of-Distribution At Test-time (namely GOODAT), a data-centric, unsupervised, and plug-and-play solution that operates independently of training data and modifications of GNN architecture. With a lightweight graph masker, GOODAT can learn informative subgraphs from test samples, enabling the capture of distinct graph patterns between OOD and ID samples. To optimize the graph masker, we meticulously design three unsupervised objective functions based on the graph information bottleneck principle, motivating the masker to capture compact yet informative subgraphs for OOD detection. Comprehensive evaluations confirm that our GOODAT method outperforms state-of-the-art benchmarks across a variety of real-world datasets.

Harnessing Edge Information for Improved Robustness in Vision Transformers

Deep Neural Networks (DNNs) have demonstrated remarkable accuracy in vision classification tasks. However, they exhibit vulnerability to additional noises known as adversarial attacks. Previous studies hypothesize that this vulnerability might stem from the fact that high-accuracy DNNs heavily rely on irrelevant and non-robust features, such as textures and the background. In this work, we reveal that edge information extracted from images can provide relevant and robust features related to shapes and the foreground. These features assist pretrained DNNs in achieving improved adversarial robustness without compromising their accuracy on clean images. A lightweight and plug-and-play EdgeNet is proposed, which can be seamlessly integrated into existing pretrained DNNs, including Vision Transformers, a recent family of state-of-the-art models for vision classification. Our EdgeNet can process edges derived from either clean nature images or noisy adversarial images, yielding robust features which can be injected into the intermediate layers of the frozen backbone DNNs. The cost of obtaining such edges using conventional edge detection algorithms (e.g., Canny edge detector) is marginal, and the cost of training the EdgeNet is equivalent to that of fine-tuning the backbone network with techniques such as Adapter.

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

The goal of this paper is to alleviate the training cost for few-shot semantic segmentation (FSS) models. Despite that FSS in nature improves model generalization to new concepts using only a handful of test exemplars, it relies on strong supervision from a considerable amount of labeled training data for base classes. However, collecting pixel-level annotations is notoriously expensive and time-consuming, and small-scale training datasets convey low information density that limits test-time generalization. To resolve the issue, we take a pioneering step towards label-efficient training of FSS models from fully unlabeled training data, or additionally a few labeled samples to enhance the performance. This motivates an approach based on a novel unsupervised meta-training paradigm. In particular, the approach first distills pre-trained unsupervised pixel embedding into compact semantic clusters from which a massive number of pseudo meta-tasks is constructed. To mitigate the noise in the pseudo meta-tasks, we further advocate a robust Transformer-based FSS model with a novel prototype-based cross-attention design. Extensive experiments have been conducted on two standard benchmarks, i.e., PASCAL-5i and COCO-20i, and the results show that our method produces impressive performance without any annotations, and is comparable to fully supervised competitors even using only 20% of the annotations. Our code is available at: https://github.com/SSSKYue/UMTFSS.

FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing

Federated Learning (FL) has emerged as a promising solution in Edge Computing (EC) environments to process the proliferation of data generated by edge devices. By collaboratively optimizing the global machine learning models on distributed edge devices, FL circumvents the need for transmitting raw data and enhances user privacy. Despite practical successes, FL still confronts significant challenges including constrained edge device resources, multiple tasks deployment, and data heterogeneity. However, existing studies focus on mitigating the FL training costs of each single task whereas neglecting the resource consumption across multiple tasks in heterogeneous FL scenarios. In this paper, we propose Heterogeneous Federated Learning with Local Parameter Sharing (FedLPS) to fill this gap. FedLPS leverages principles from transfer learning to facilitate the deployment of multiple tasks on a single device by dividing the local model into a shareable encoder and task-specific encoders. To further reduce resource consumption, a channel-wise model pruning algorithm that shrinks the footprint of local models while accounting for both data and system heterogeneity is employed in FedLPS. Additionally, a novel heterogeneous model aggregation algorithm is proposed to aggregate the heterogeneous predictors in FedLPS. We implemented the proposed FedLPS on a real FL platform and compared it with state-of-the-art (SOTA) FL frameworks. The experimental results on five popular datasets and two modern DNN models illustrate that the proposed FedLPS significantly outperforms the SOTA FL frameworks by up to 4.88% and reduces the computational resource consumption by 21.3%. Our code is available at: https://github.com/jyzgh/FedLPS.

Compound Text-Guided Prompt Tuning via Image-Adaptive Cues

Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable generalization capabilities to downstream tasks. However, existing prompt tuning based frameworks need to parallelize learnable textual inputs for all categories, suffering from massive GPU memory consumption when there is a large number of categories in the target dataset. Moreover, previous works require to include category names within prompts, exhibiting subpar performance when dealing with ambiguous category names. To address these shortcomings, we propose Compound Text-Guided Prompt Tuning (TGP-T) that significantly reduces resource demand while achieving superior performance. We introduce text supervision to the optimization of prompts, which enables two benefits: 1) releasing the model reliance on the pre-defined category names during inference, thereby enabling more flexible prompt generation; 2) reducing the number of inputs to the text encoder, which decreases GPU memory consumption significantly. Specifically, we found that compound text supervisions, i.e., category-wise and content-wise, is highly effective, since they provide inter-class separability and capture intra-class variations, respectively. Moreover, we condition the prompt generation on visual features through a module called Bonder, which facilitates the alignment between prompts and visual features. Extensive experiments on few-shot recognition and domain generalization demonstrate that TGP-T achieves superior performance with consistently lower training costs. It reduces GPU memory usage by 93% and attains a 2.5% performance gain on 16-shot ImageNet. The code is available at https://github.com/EricTan7/TGP-T.

Patch-Aware Sample Selection for Efficient Masked Image Modeling

Nowadays sample selection is drawing increasing attention. By extracting and training only on the most informative subset, sample selection can effectively reduce the training cost. Although sample selection is effective in conventional supervised learning, applying it to Masked Image Modeling (MIM) still poses challenges due to the gap between sample-level selection and patch-level pre-training. In this paper, we inspect the sample selection in MIM pre-training and find the basic selection suffers from performance degradation. We attribute this degradation primarily to 2 factors: the random mask strategy and the simple averaging function. We then propose Patch-Aware Sample Selection (PASS), including a low-cost Dynamic Trained Mask Predictor (DTMP) and Weighted Selection Score (WSS). DTMP consistently masks the informative patches in samples, ensuring a relatively accurate representation of selection score. WSS enhances the selection score using patch-level disparity. Extensive experiments show the effectiveness of PASS in selecting the most informative subset and accelerating pretraining. PASS exhibits superior performance across various datasets, MIM methods, and downstream tasks. Particularly, PASS improves MAE by 0.7% on ImageNet-1K while utilizing only 37% data budget and achieves ~1.7x speedup.

From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery

Molecule discovery serves as a cornerstone in numerous scientific domains, fueling the development of new materials and innovative drug designs. Recent developments of in-silico molecule discovery have highlighted the promising results of cross-modal techniques, which bridge molecular structures with their descriptive annotations. However, these cross-modal methods frequently encounter the issue of data scarcity, hampering their performance and application. In this paper, we address the low-resource challenge by utilizing artificially-real data generated by Large Language Models (LLMs). We first introduce a retrieval-based prompting strategy to construct high-quality pseudo data, then explore the optimal method to effectively leverage this pseudo data. Experiments show that using pseudo data for domain adaptation outperforms all existing methods, while also requiring a smaller model scale, reduced data size and lower training cost, highlighting its efficiency. Furthermore, our method shows a sustained improvement as the volume of pseudo data increases, revealing the great potential of pseudo data in advancing low-resource cross-modal molecule discovery.

LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection

Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps). Considering log data of variant domains, retraining the whole network for unknown domains is inefficient in real industrial scenarios. However, previous deep models merely focused on extracting the semantics of log sequences in the same domain, leading to poor generalization on multi-domain logs. To alleviate this issue, we propose a unified Transformer-based framework for Log anomaly detection (LogFormer) to improve the generalization ability across different domains, where we establish a two-stage process including the pre-training and adapter-based tuning stage. Specifically, our model is first pre-trained on the source domain to obtain shared semantic knowledge of log data. Then, we transfer such knowledge to the target domain via shared parameters. Besides, the Log-Attention module is proposed to supplement the information ignored by the log-paring. The proposed method is evaluated on three public datasets and one real-world dataset. Experimental results on multiple benchmarks demonstrate the effectiveness of our LogFormer with fewer trainable parameters and lower training costs.

Efficient Target Propagation by Deriving Analytical Solution

Exploring biologically plausible algorithms as alternatives to error backpropagation (BP) is a challenging research topic in artificial intelligence. It also provides insights into the brain's learning methods. Recently, when combined with well-designed feedback loss functions such as Local Difference Reconstruction Loss (LDRL) and through hierarchical training of feedback pathway synaptic weights, Target Propagation (TP) has achieved performance comparable to BP in image classification tasks. However, with an increase in the number of network layers, the tuning and training cost of feedback weights escalates. Drawing inspiration from the work of Ernoult et al., we propose a training method that seeks the optimal solution for feedback weights. This method enhances the efficiency of feedback training by analytically minimizing feedback loss, allowing the feedback layer to skip certain local training iterations. More specifically, we introduce the Jacobian matching loss (JML) for feedback training. We also proactively implement layers designed to derive analytical solutions that minimize JML. Through experiments, we have validated the effectiveness of this approach. Using the CIFAR-10 dataset, our method showcases accuracy levels comparable to state-of-the-art TP methods. Furthermore, we have explored its effectiveness in more intricate network architectures.

Towards Continual Knowledge Graph Embedding via Incremental Distillation

Traditional knowledge graph embedding (KGE) methods typically require preserving the entire knowledge graph (KG) with significant training costs when new knowledge emerges. To address this issue, the continual knowledge graph embedding (CKGE) task has been proposed to train the KGE model by learning emerging knowledge efficiently while simultaneously preserving decent old knowledge. However, the explicit graph structure in KGs, which is critical for the above goal, has been heavily ignored by existing CKGE methods. On the one hand, existing methods usually learn new triples in a random order, destroying the inner structure of new KGs. On the other hand, old triples are preserved with equal priority, failing to alleviate catastrophic forgetting effectively. In this paper, we propose a competitive method for CKGE based on incremental distillation (IncDE), which considers the full use of the explicit graph structure in KGs. First, to optimize the learning order, we introduce a hierarchical strategy, ranking new triples for layer-by-layer learning. By employing the inter- and intra-hierarchical orders together, new triples are grouped into layers based on the graph structure features. Secondly, to preserve the old knowledge effectively, we devise a novel incremental distillation mechanism, which facilitates the seamless transfer of entity representations from the previous layer to the next one, promoting old knowledge preservation. Finally, we adopt a two-stage training paradigm to avoid the over-corruption of old knowledge influenced by under-trained new knowledge. Experimental results demonstrate the superiority of IncDE over state-of-the-art baselines. Notably, the incremental distillation mechanism contributes to improvements of 0.2%-6.5% in the mean reciprocal rank (MRR) score. More exploratory experiments validate the effectiveness of IncDE in proficiently learning new knowledge while preserving old knowledge across all time steps.

LMD: Faster Image Reconstruction with Latent Masking Diffusion

As a class of fruitful approaches, diffusion probabilistic models (DPMs) have shown excellent advantages in high-resolution image reconstruction. On the other hand, masked autoencoders (MAEs), as popular self-supervised vision learners, have demonstrated simpler and more effective image reconstruction and transfer capabilities on downstream tasks. However, they all require extremely high training costs, either due to inherent high temporal-dependence (i.e., excessively long diffusion steps) or due to artificially low spatial-dependence (i.e., human-formulated high mask ratio, such as 0.75). To the end, this paper presents LMD, a faster image reconstruction framework with Latent Masking Diffusion. First, we propose to project and reconstruct images in latent space through a pre-trained variational autoencoder, which is theoretically more efficient than in the pixel-based space. Then, we combine the advantages of MAEs and DPMs to design a progressive masking diffusion model, which gradually increases the masking proportion by three different schedulers and reconstructs the latent features from simple to difficult, without sequentially performing denoising diffusion as in DPMs or using fixed high masking ratio as in MAEs, so as to alleviate the high training time-consumption predicament. Our approach allows for learning high-capacity models and accelerate their training (by 3x or more) and barely reduces the original accuracy. Inference speed in downstream tasks also significantly outperforms the previous approaches.

Tackling Vision Language Tasks through Learning Inner Monologues

Visual language tasks such as Visual Question Answering (VQA) or Visual Entailment (VE) require AI models to comprehend and reason with both visual and textual content. Driven by the power of Large Language Models (LLMs), two prominent methods have emerged: (1) the hybrid integration between LLMs and Vision-Language Models (VLMs), where visual inputs are firstly converted into language descriptions by VLMs, serving as inputs for LLMs to generate final answer(s); (2) visual feature alignment in language space, where visual inputs are encoded as embeddings and projected to LLMs' language space via further supervised fine-tuning. The first approach provides light training costs and interpretability but is hard to be optimized in an end-to-end fashion. The second approach presents decent performance, but feature alignment usually requires large amounts of training data and lacks interpretability. To tackle this dilemma, we propose a novel approach, Inner Monologue Multi-Modal Optimization (IMMO), to solve complex vision language problems by simulating Inner Monologue, a cognitive process in which an individual engages in silent verbal communication with themselves. More specifically, we enable LLMs and VLMs to interact through natural language conversation (i.e., Inner Monologue) and propose to use a two-stage training process to learn how to do Inner Monologue (self-asking questions and answering questions). IMMO is evaluated on two popular tasks and achieves competitive performance with less training data when compared with state-of-the-art models while concurrently keeping the interpretability. The results suggest that by emulating the cognitive phenomenon of internal dialogue, our approach can enhance reasoning and explanation abilities, contributing to the more effective fusion of vision and language models. More importantly, instead of using predefined human-crafted monologues, IMMO learns this process within the deep learning models, broadening its potential applications across various AI challenges beyond vision and language tasks.

Procedural Level Generation with Diffusion Models from a Single Example

Level generation is a central focus of Procedural Content Generation (PCG), yet deep learning-based approaches are limited by scarce training data, i.e., human-designed levels. Despite being a dominant framework, Generative Adversarial Networks (GANs) exhibit a substantial quality gap between generated and human-authored levels, alongside rising training costs, particularly with increasing token complexity. In this paper, we introduce a diffusion-based generative model that learns from just one example. Our approach involves two core components: 1) an efficient yet expressive level representation, and 2) a latent denoising network with constrained receptive fields. To start with, our method utilizes token semantic labels, similar to word embeddings, to provide dense representations. This strategy not only surpasses one-hot encoding in representing larger game levels but also improves stability and accelerates convergence in latent diffusion. In addition, we adapt the denoising network architecture to confine the receptive field to localized patches of the data, aiming to facilitate single-example learning. Extensive experiments demonstrate that our model is capable of generating stylistically congruent samples of arbitrary sizes compared to manually designed levels. It suits a wide range of level structures with fewer artifacts than GAN-based approaches. The source code is available at https://github.com/shiqi-dai/diffusioncraft.

NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views

Recently, neural implicit functions have demonstrated remarkable results in the field of multi-view reconstruction. However, most existing methods are tailored for dense views and exhibit unsatisfactory performance when dealing with sparse views. Several latest methods have been proposed for generalizing implicit reconstruction to address the sparse view reconstruction task, but they still suffer from high training costs and are merely valid under carefully selected perspectives. In this paper, we propose a novel sparse view reconstruction framework that leverages on-surface priors to achieve highly faithful surface reconstruction. Specifically, we design several constraints on global geometry alignment and local geometry refinement for jointly optimizing coarse shapes and fine details. To achieve this, we train a neural network to learn a global implicit field from the on-surface points obtained from SfM and then leverage it as a coarse geometric constraint. To exploit local geometric consistency, we project on-surface points onto seen and unseen views, treating the consistent loss of projected features as a fine geometric constraint. The experimental results with DTU and BlendedMVS datasets in two prevalent sparse settings demonstrate significant improvements over the state-of-the-art methods.

CAR-Transformer: Cross-Attention Reinforcement Transformer for Cross-Lingual Summarization

Cross-Lingual Summarization (CLS) involves generating a summary for a given document in another language. Most of the existing approaches adopt multi-task training and knowledge distillation, which increases the training cost and improves the performance of CLS tasks intuitively but unexplainably. In this work, we propose Cross-Attention Reinforcement (CAR) module and incorporate the module into the transformer backbone to formulate the CAR-Transformer. The CAR module formulates a pseudo summarization policy parameterized by the cross-attention weights reinforced by the ground-truth monolingual summary without introducing extra model parameters. Our approach demonstrates more consistent improvement across CLS tasks compared to traditional multi-task training methods and outperforms the fine-tuned vanilla mBART by 3.67 and the best-performing multi-task training approach by 1.48 in ROUGE-L F1 score on the WikiLingua Korean-to-English CLS task.

CR-SAM: Curvature Regularized Sharpness-Aware Minimization

The capacity to generalize to future unseen data stands as one of the utmost crucial attributes of deep neural networks. Sharpness-Aware Minimization (SAM) aims to enhance the generalizability by minimizing worst-case loss using one-step gradient ascent as an approximation. However, as training progresses, the non-linearity of the loss landscape increases, rendering one-step gradient ascent less effective. On the other hand, multi-step gradient ascent will incur higher training cost. In this paper, we introduce a normalized Hessian trace to accurately measure the curvature of loss landscape on both training and test sets. In particular, to counter excessive non-linearity of loss landscape, we propose Curvature Regularized SAM (CR-SAM), integrating the normalized Hessian trace as a SAM regularizer. Additionally, we present an efficient way to compute the trace via finite differences with parallelism. Our theoretical analysis based on PAC-Bayes bounds establishes the regularizer's efficacy in reducing generalization error. Empirical evaluation on CIFAR and ImageNet datasets shows that CR-SAM consistently enhances classification performance for ResNet and Vision Transformer (ViT) models across various datasets. Our code is available at https://github.com/TrustAIoT/CR-SAM.

Cautiously-Optimistic Knowledge Sharing for Cooperative Multi-Agent Reinforcement Learning

While decentralized training is attractive in multi-agent reinforcement learning (MARL) for its excellent scalability and robustness, its inherent coordination challenges in collaborative tasks result in numerous interactions for agents to learn good policies. To alleviate this problem, action advising methods make experienced agents share their knowledge about what to do, while less experienced agents strictly follow the received advice. However, this method of sharing and utilizing knowledge may hinder the team's exploration of better states, as agents can be unduly influenced by suboptimal or even adverse advice, especially in the early stages of learning. Inspired by the fact that humans can learn not only from the success but also from the failure of others, this paper proposes a novel knowledge sharing framework called Cautiously-Optimistic kNowledge Sharing (CONS). CONS enables each agent to share both positive and negative knowledge and cautiously assimilate knowledge from others, thereby enhancing the efficiency of early-stage exploration and the agents' robustness to adverse advice. Moreover, considering the continuous improvement of policies, agents value negative knowledge more in the early stages of learning and shift their focus to positive knowledge in the later stages. Our framework can be easily integrated into existing Q-learning based methods without introducing additional training costs. We evaluate CONS in several challenging multi-agent tasks and find it excels in environments where optimal behavioral patterns are difficult to discover, surpassing the baselines in terms of convergence rate and final performance.

Neural Embeddings for kNN Search in Biological Sequence

Biological sequence nearest neighbor search plays a fundamental role in bioinformatics. To alleviate the pain of quadratic complexity for conventional distance computation, neural distance embeddings, which project sequences into geometric space, have been recognized as a promising paradigm. To maintain the distance order between sequences, these models all deploy triplet loss and use intuitive methods to select a subset of triplets for training from a vast selection space. However, we observed that such training often enables models to distinguish only a fraction of distance orders, leaving others unrecognized. Moreover, naively selecting more triplets for training under the state-of-the-art network not only adds costs but also hampers model performance. In this paper, we introduce Bio-kNN: a kNN search framework for biological sequences. It includes a systematic triplet selection method and a multi-head network, enhancing the discernment of all distance orders without increasing training expenses. Initially, we propose a clustering-based approach to partition all triplets into several clusters with similar properties, and then select triplets from these clusters using an innovative strategy. Meanwhile, we noticed that simultaneously training different types of triplets in the same network cannot achieve the expected performance, thus we propose a multi-head network to tackle this. Our network employs a convolutional neural network(CNN) to extract local features shared by all clusters, and then learns a multi-layer perception(MLP) head for each cluster separately. Besides, we treat CNN as a special head, thereby integrating crucial local features which are neglected in previous models into our model for similarity recognition. Extensive experiments show that our Bio-kNN significantly outperforms the state-of-the-art methods on two large-scale datasets without increasing the training cost.

LDS2AE: Local Diffusion Shared-Specific Autoencoder for Multimodal Remote Sensing Image Classification with Arbitrary Missing Modalities

Recent research on the joint classification of multimodal remote sensing data has achieved great success. However, due to the limitations imposed by imaging conditions, the case of missing modalities often occurs in practice. Most previous researchers regard the classification in case of different missing modalities as independent tasks. They train a specific classification model for each fixed missing modality by extracting multimodal joint representation, which cannot handle the classification of arbitrary (including multiple and random) missing modalities. In this work, we propose a local diffusion shared-specific autoencoder (LDS2AE), which solves the classification of arbitrary missing modalities with a single model. The LDS2AE captures the data distribution of different modalities to learn multimodal shared feature for classification by designing a novel local diffusion autoencoder which consists of a modality-shared encoder and several modality-specific decoders. The modality-shared encoder is designed to extract multimodal shared feature by employing the same parameters to map multimodal data into a shared subspace. The modality-specific decoders put the multimodal shared feature to reconstruct the image of each modality, which facilitates the shared feature to learn unique information of different modalities. In addition, we incorporate masked training to the diffusion autoencoder to achieve local diffusion, which significantly reduces the training cost of model. The approach is tested on widely-used multimodal remote sensing datasets, demonstrating the effectiveness of the proposed LDS2AE in addressing the classification of arbitrary missing modalities. The code is available at https://github.com/Jiahuiqu/LDS2AE.

Physics-informed neural network for simulating magnetic field of coaxial magnetic gear

In the process of performance analysis and structure optimization of coaxial magnetic gear, an emerging method for precise magnetic field simulation remains a focal point in engineering research. In this study, we introduce a physics-informed neural network to model the magnetic field of a magnetic gear. We employed a physics-based loss function to optimize neural network parameters to solve the magnetic field of a Maxwell-controlled magnetic gear. Additionally, we developed a joint training model that leverages the continuity of the medium interface. The feasibility of the model was confirmed by solving the magnetic field of a permanent magnet, with an error margin of less than 5%. The model exhibited excellent precision in simulating magnetic field behavior within magnetic gears. We demonstrate that adjusting model parameters enables the creation of a proxy model, which effectively addresses analogous problems. Furthermore, leveraging transfer learning substantially diminishes training time for similar tasks, resulting in a 43% reduction in training cost. Finally, we propose an enhanced physical information neural network with data-physical drive fusion and use a special Poisson's equation solution in the magnetized region as a data drive during training. The enhanced physics-informed neural network effectively solved the magnetic field of a magnetic gear, resulting in a 50% improvement in solution accuracy. This study establishes the groundwork for analyzing and optimizing magnetic gears, providing new research insight for electromagnetic practitioners.