Heterogeneous information networks (HIN) have gained increasing popularity for being able to capture complex relations between nodes of diverse types. Meta-structure was proposed to identify important patterns of relations on HIN, which has been proven effective for extracting rich semantic information and facilitating graph neural networks to learn expressive representations. However, hand-crafted meta-structures pose challenges for scaling up, which draws wide research attention for developing automatic meta-structure search algorithms. Previous efforts concentrate on searching for meta-structures with good empirical prediction performance, overlooking explainability. Thus, they often produce meta-structures prone to overfitting and incomprehensible to humans. To address this, we draw inspiration from the emergent reasoning abilities of large language models (LLMs). We propose a novel REasoning meta-STRUCTure search (ReStruct) framework that integrates LLM reasoning into the evolutionary procedure. ReStruct uses a grammar translator to encode meta-structures into natural language sentences, and leverages the reasoning power of LLMs to evaluate semantically feasible meta-structures. ReStruct also employs performance-oriented evolutionary operations. These two competing forces jointly optimize for semantic explainability and empirical performance of meta-structures. We also design a differential LLM explainer that can produce natural language explanations for the discovered meta-structures, and refine the explanation by reasoning through the search history. Experiments on five datasets demonstrate ReStruct achieve SOTA performance in node classification and link recommendation tasks. Additionally, a survey study involving 73 graduate students shows that the meta-structures and natural language explanations generated by ReStruct are substantially more comprehensible.
Speeding up the large-scale distributed training is challenging in that it requires improving various components of training including load balancing, communication, optimizers, etc. We present novel approaches for fast large-scale training of BERT model which individually ameliorates each component thereby leading to a new level of BERT training performance. Load balancing is imperative in distributed BERT training since its training datasets are characterized by samples with various lengths. Communication cost, which is proportional to the scale of distributed training, needs to be hidden by useful computation. In addition, the optimizers, e.g., ADAM, LAMB, etc., need to be carefully re-evaluated in the context of large-scale distributed training. We propose two new ideas, (1) local presorting based on dataset stratification for load balancing and (2) bucket-wise gradient clipping before allreduce which allows us to benefit from the overlap of gradient computation and synchronization as well as the fast training of gradient clipping before allreduce. We also re-evaluate existing optimizers via hyperparameter optimization and utilize ADAM, which also contributes to fast training via larger batches than existing methods. Our proposed methods, all combined, give the fastest MLPerf BERT training of 25.1 (22.3) seconds on 1,024 NVIDIA A100 GPUs, which is 1.33x (1.13x) and 1.57x faster than the other top two (one) submissions to MLPerf v1.1 (v2.0). Our implementation and evaluation results are available at MLPerf v1.1~v2.1.
In this work, a tensor completion problem is studied, which aims to perfectly recover the tensor from partial observations. Existing theoretical guarantee requires the involved transform to be orthogonal, which hinders its applications. In this paper, jumping out of the constraints of isotropy or self-adjointness, the theoretical guarantee of exact tensor completion with arbitrary linear transforms is established. To that end, we define a new tensor-tensor product, which leads us to a new definition of the tensor nuclear norm. Equipped with these tools, an efficient algorithm based on alternating direction of multipliers is designed to solve the transformed tensor completion program and the theoretical bound is obtained. Our model and proof greatly enhance the flexibility of tensor completion and extensive experiments validate the superiority of the proposed method.
Due to the rise of privacy concerns, in many practical applications the training data is aggregated before being shared with the learner, in order to protect privacy of users' sensitive responses. In an aggregate learning framework, the dataset is grouped into bags of samples, where each bag is available only with an aggregate response, providing a summary of individuals' responses in that bag. In this paper, we study two natural loss functions for learning from aggregate responses: bag-level loss and the instance-level loss. In the former, the model is learnt by minimizing a loss between aggregate responses and aggregate model predictions, while in the latter the model aims to fit individual predictions to the aggregate responses. In this work, we show that the instance-level loss can be perceived as a regularized form of the bag-level loss. This observation lets us compare the two approaches with respect to bias and variance of the resulting estimators, and introduce a novel interpolating estimator which combines the two approaches. For linear regression tasks, we provide a precise characterization of the risk of the interpolating estimator in an asymptotic regime where the size of the training set grows in proportion to the features dimension. Our analysis allows us to theoretically understand the effect of different factors, such as bag size on the model prediction risk. In addition, we propose a mechanism for differentially private learning from aggregate responses and derive the optimal bag size in terms of prediction risk-privacy trade-off. We also carry out thorough experiments to corroborate our theory and show the efficacy of the interpolating estimator.
Federated learning (FL) has shown remarkable success in cooperatively training deep models, while typically struggling with noisy labels. Advanced works propose to tackle label noise by a re-weighting strategy with a strong assumption, i.e., mild label noise. However, it may be violated in many real-world FL scenarios because of highly contaminated clients, resulting in extreme noise ratios, e.g., $>$90%. To tackle extremely noisy clients, we study the robustness of the re-weighting strategy, showing a pessimistic conclusion: minimizing the weight of clients trained over noisy data outperforms re-weighting strategies. To leverage models trained on noisy clients, we propose a novel approach, called negative distillation (FedNed). FedNed first identifies noisy clients and employs rather than discards the noisy clients in a knowledge distillation manner. In particular, clients identified as noisy ones are required to train models using noisy labels and pseudo-labels obtained by global models. The model trained on noisy labels serves as a `bad teacher' in knowledge distillation, aiming to decrease the risk of providing incorrect information. Meanwhile, the model trained on pseudo-labels is involved in model aggregation if not identified as a noisy client. Consequently, through pseudo-labeling, FedNed gradually increases the trustworthiness of models trained on noisy clients, while leveraging all clients for model aggregation through negative distillation. To verify the efficacy of FedNed, we conduct extensive experiments under various settings, demonstrating that FedNed can consistently outperform baselines and achieve state-of-the-art performance. Our code is available at https://github.com/linChen99/FedNed.
Lumbar disc herniation (LDH) is a prevalent orthopedic condition in clinical practice. Inertial measurement unit sensors (IMUs) are an effective tool for monitoring and assessing gait impairment in patients with lumbar disc herniation (LDH). However, the current gait assessment of LDH focuses solely on single-source acceleration signal data, without considering the diversity of sensor data. It also overlooks the individual differences in motor function deterioration between the healthy and affected lower limbs in patients with LDH. To address this issue, we developed an LDH gait feature model that relies on multi-source adaptive Kalman data fusion of acceleration and angular velocity. We utilized an adaptive Kalman data fusion algorithm for acceleration and angular velocity to estimate the attitude angle and segment the gait phase. Two Inertial Measurement Units (IMUs) were used to analyze the gait characteristics of patients with lumbar disc issues and healthy individuals. This analysis included 12 gait characteristics, such as gait spatiotemporal parameters, kinematic parameters, and expansibility index numbers. Statistical methods were employed to analyze the characteristic model and confirm the biological differences between the healthy affected side of LDH and healthy subjects. Finally, a classifier based on feature engineering was utilized to classify the gait patterns of the affected side of patients with lumbar disc disease and healthy subjects. This approach achieved a classification accuracy of 95.50%, enhancing the recognition of LDH and healthy gait patterns. It also provided effective gait feature sets and methods for assessing LDH clinically.
In this paper, we first assess and harness various Vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely Rein, to parameter-efficiently harness VFMs for DGSS. Built upon a set of trainable tokens, each linked to distinct instances, Rein precisely refines and forwards the feature maps from each layer to the next layer within the backbone. This process produces diverse refinements for different categories within a single image. With fewer trainable parameters, Rein efficiently fine-tunes VFMs for DGSS tasks, surprisingly surpassing full parameter fine-tuning. Extensive experiments across various settings demonstrate that Rein significantly outperforms state-of-the-art methods. Remarkably, with just an extra 1% of trainable parameters within the frozen backbone, Rein achieves a mIoU of 68.1% on the Cityscapes, without accessing any real urban-scene datasets.Code is available at https://github.com/w1oves/Rein.git.
In the realm of large multi-modal models (LMMs), efficient modality alignment is crucial yet often constrained by the scarcity of high-quality image-text data. To address this bottleneck, we introduce the ShareGPT4V dataset, a pioneering large-scale resource featuring 1.2 million highly descriptive captions, which surpasses existing datasets in diversity and information content, covering world knowledge, object properties, spatial relationships, and aesthetic evaluations. Specifically, ShareGPT4V originates from a curated 100K high-quality captions collected from advanced GPT4-Vision and has been expanded to 1.2M with a superb caption model trained on this subset. ShareGPT4V first demonstrates its effectiveness for the Supervised Fine-Tuning (SFT) phase, by substituting an equivalent quantity of detailed captions in existing SFT datasets with a subset of our high-quality captions, significantly enhancing the LMMs like LLaVA-7B, LLaVA-1.5-13B, and Qwen-VL-Chat-7B on the MME and MMBench benchmarks, with respective gains of 222.8/22.0/22.3 and 2.7/1.3/1.5. We further incorporate ShareGPT4V data into both the pre-training and SFT phases, obtaining ShareGPT4V-7B, a superior LMM based on a simple architecture that has remarkable performance across a majority of the multi-modal benchmarks. This project is available at https://ShareGPT4V.github.io to serve as a pivotal resource for advancing the LMMs community.