Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

Low-rank training has emerged as a promising approach for reducing memory usage in training Large Language Models (LLMs). Previous methods either rely on decomposing weight matrices (e.g., LoRA), or seek to decompose gradient matrices (e.g., GaLore) to ensure reduced memory consumption. However, both of them constrain the training in a low-rank subspace, thus inevitably leading to sub-optimal performance. This raises a question: whether it is possible to consistently preserve the low-rank constraint for memory efficiency, while achieving full-rank training (i.e., training with full-rank gradients of full-rank weights) to avoid inferior outcomes? In this paper, we propose a new plug-and-play training framework for LLMs called Fira, as the first attempt to achieve this goal. First, we observe an interesting phenomenon during LLM training: the scaling impact of adaptive optimizers (e.g., Adam) on the gradient norm remains similar from low-rank to full-rank training. Based on this observation, we propose a norm-based scaling method, which utilizes the scaling impact of low-rank optimizers as substitutes for that of original full-rank optimizers to enable full-rank training. In this way, we can preserve the low-rank constraint in the optimizer while achieving full-rank training for better performance. Moreover, we find that there are sudden gradient rises during the optimization process, potentially causing loss spikes. To address this, we further put forward a norm-growth limiter to smooth the gradient via regulating the relative increase of gradient norms. Extensive experiments on the pre-training and fine-tuning of LLMs show that Fira outperforms both LoRA and GaLore, achieving performance that is comparable to or even better than full-rank training.

Keypoint-based Progressive Chain-of-Thought Distillation for LLMs

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale produced by LLMs, often facing the following challenges: (i) Tokens within a rationale vary in significance, and treating them equally may fail to accurately mimic keypoint tokens, leading to reasoning errors. (ii) They usually distill knowledge by consistently predicting all the steps in a rationale, which falls short in distinguishing the learning order of step generation. This diverges from the human cognitive progression of starting with easy tasks and advancing to harder ones, resulting in sub-optimal outcomes. To this end, we propose a unified framework, called KPOD, to address these issues. Specifically, we propose a token weighting module utilizing mask learning to encourage accurate mimicry of keypoint tokens by the student during distillation. Besides, we develop an in-rationale progressive distillation strategy, starting with training the student to generate the final reasoning steps and gradually extending to cover the entire rationale. To accomplish this, a weighted token generation loss is proposed to assess step reasoning difficulty, and a value function is devised to schedule the progressive distillation by considering both step difficulty and question diversity. Extensive experiments on four reasoning benchmarks illustrate our KPOD outperforms previous methods by a large margin.

On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving

End-to-end motion planning models equipped with deep neural networks have shown great potential for enabling full autonomous driving. However, the oversized neural networks render them impractical for deployment on resource-constrained systems, which unavoidably requires more computational time and resources during reference.To handle this, knowledge distillation offers a promising approach that compresses models by enabling a smaller student model to learn from a larger teacher model. Nevertheless, how to apply knowledge distillation to compress motion planners has not been explored so far. In this paper, we propose PlanKD, the first knowledge distillation framework tailored for compressing end-to-end motion planners. First, considering that driving scenes are inherently complex, often containing planning-irrelevant or even noisy information, transferring such information is not beneficial for the student planner. Thus, we design an information bottleneck based strategy to only distill planning-relevant information, rather than transfer all information indiscriminately. Second, different waypoints in an output planned trajectory may hold varying degrees of importance for motion planning, where a slight deviation in certain crucial waypoints might lead to a collision. Therefore, we devise a safety-aware waypoint-attentive distillation module that assigns adaptive weights to different waypoints based on the importance, to encourage the student to accurately mimic more crucial waypoints, thereby improving overall safety. Experiments demonstrate that our PlanKD can boost the performance of smaller planners by a large margin, and significantly reduce their reference time.

Learning to Generate Parameters of ConvNets for Unseen Image Data

Typical Convolutional Neural Networks (ConvNets) depend heavily on large amounts of image data and resort to an iterative optimization algorithm (e.g., SGD or Adam) to learn network parameters, which makes training very time- and resource-intensive. In this paper, we propose a new training paradigm and formulate the parameter learning of ConvNets into a prediction task: given a ConvNet architecture, we observe there exists correlations between image datasets and their corresponding optimal network parameters, and explore if we can learn a hyper-mapping between them to capture the relations, such that we can directly predict the parameters of the network for an image dataset never seen during the training phase. To do this, we put forward a new hypernetwork based model, called PudNet, which intends to learn a mapping between datasets and their corresponding network parameters, and then predicts parameters for unseen data with only a single forward propagation. Moreover, our model benefits from a series of adaptive hyper recurrent units sharing weights to capture the dependencies of parameters among different network layers. Extensive experiments demonstrate that our proposed method achieves good efficacy for unseen image datasets on two kinds of settings: Intra-dataset prediction and Inter-dataset prediction. Our PudNet can also well scale up to large-scale datasets, e.g., ImageNet-1K. It takes 8967 GPU seconds to train ResNet-18 on the ImageNet-1K using GC from scratch and obtain a top-5 accuracy of 44.65 %. However, our PudNet costs only 3.89 GPU seconds to predict the network parameters of ResNet-18 achieving comparable performance (44.92 %), more than 2,300 times faster than the traditional training paradigm.

Shared Growth of Graph Neural Networks via Free-direction Knowledge Distillation

Knowledge distillation (KD) has shown to be effective to boost the performance of graph neural networks (GNNs), where the typical objective is to distill knowledge from a deeper teacher GNN into a shallower student GNN. However, it is often quite challenging to train a satisfactory deeper GNN due to the well-known over-parametrized and over-smoothing issues, leading to invalid knowledge transfer in practical applications. In this paper, we propose the first Free-direction Knowledge Distillation framework via reinforcement learning for GNNs, called FreeKD, which is no longer required to provide a deeper well-optimized teacher GNN. Our core idea is to collaboratively learn two shallower GNNs in an effort to exchange knowledge between them via reinforcement learning in a hierarchical way. As we observe that one typical GNN model often exhibits better and worse performances at different nodes during training, we devise a dynamic and free-direction knowledge transfer strategy that involves two levels of actions: 1) node-level action determines the directions of knowledge transfer between the corresponding nodes of two networks; and then 2) structure-level action determines which of the local structures generated by the node-level actions to be propagated. Furthermore, considering the diverse knowledge present in different GNNs when dealing with multi-view inputs, we introduce FreeKD++ as a solution to enable free-direction knowledge transfer among multiple shallow GNNs operating on multi-view inputs. Extensive experiments on five benchmark datasets demonstrate our approaches outperform the base GNNs in a large margin, and shows their efficacy to various GNNs. More surprisingly, our FreeKD has comparable or even better performance than traditional KD algorithms that distill knowledge from a deeper and stronger teacher GNN.

Towards Open Temporal Graph Neural Networks

Graph neural networks (GNNs) for temporal graphs have recently attracted increasing attentions, where a common assumption is that the class set for nodes is closed. However, in real-world scenarios, it often faces the open set problem with the dynamically increased class set as the time passes by. This will bring two big challenges to the existing dynamic GNN methods: (i) How to dynamically propagate appropriate information in an open temporal graph, where new class nodes are often linked to old class nodes. This case will lead to a sharp contradiction. This is because typical GNNs are prone to make the embeddings of connected nodes become similar, while we expect the embeddings of these two interactive nodes to be distinguishable since they belong to different classes. (ii) How to avoid catastrophic knowledge forgetting over old classes when learning new classes occurred in temporal graphs. In this paper, we propose a general and principled learning approach for open temporal graphs, called OTGNet, with the goal of addressing the above two challenges. We assume the knowledge of a node can be disentangled into class-relevant and class-agnostic one, and thus explore a new message passing mechanism by extending the information bottleneck principle to only propagate class-agnostic knowledge between nodes of different classes, avoiding aggregating conflictive information. Moreover, we devise a strategy to select both important and diverse triad sub-graph structures for effective class-incremental learning. Extensive experiments on three real-world datasets of different domains demonstrate the superiority of our method, compared to the baselines.

Robust Knowledge Adaptation for Dynamic Graph Neural Networks

Graph structured data often possess dynamic characters in nature, e.g., the addition of links and nodes, in many real-world applications. Recent years have witnessed the increasing attentions paid to dynamic graph neural networks for modelling such graph data, where almost all the existing approaches assume that when a new link is built, the embeddings of the neighbor nodes should be updated by learning the temporal dynamics to propagate new information. However, such approaches suffer from the limitation that if the node introduced by a new connection contains noisy information, propagating its knowledge to other nodes is not reliable and even leads to the collapse of the model. In this paper, we propose AdaNet: a robust knowledge Adaptation framework via reinforcement learning for dynamic graph neural Networks. In contrast to previous approaches immediately updating the embeddings of the neighbor nodes once adding a new link, AdaNet attempts to adaptively determine which nodes should be updated because of the new link involved. Considering that the decision whether to update the embedding of one neighbor node will have great impact on other neighbor nodes, we thus formulate the selection of node update as a sequence decision problem, and address this problem via reinforcement learning. By this means, we can adaptively propagate knowledge to other nodes for learning robust node embedding representations. To the best of our knowledge, our approach constitutes the first attempt to explore robust knowledge adaptation via reinforcement learning for dynamic graph neural networks. Extensive experiments on three benchmark datasets demonstrate that AdaNet achieves the state-of-the-art performance. In addition, we perform the experiments by adding different degrees of noise into the dataset, quantitatively and qualitatively illustrating the robustness of AdaNet.

FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks

Knowledge distillation (KD) has demonstrated its effectiveness to boost the performance of graph neural networks (GNNs), where its goal is to distill knowledge from a deeper teacher GNN into a shallower student GNN. However, it is actually difficult to train a satisfactory teacher GNN due to the well-known over-parametrized and over-smoothing issues, leading to invalid knowledge transfer in practical applications. In this paper, we propose the first Free-direction Knowledge Distillation framework via Reinforcement learning for GNNs, called FreeKD, which is no longer required to provide a deeper well-optimized teacher GNN. The core idea of our work is to collaboratively build two shallower GNNs in an effort to exchange knowledge between them via reinforcement learning in a hierarchical way. As we observe that one typical GNN model often has better and worse performances at different nodes during training, we devise a dynamic and free-direction knowledge transfer strategy that consists of two levels of actions: 1) node-level action determines the directions of knowledge transfer between the corresponding nodes of two networks; and then 2) structure-level action determines which of the local structures generated by the node-level actions to be propagated. In essence, our FreeKD is a general and principled framework which can be naturally compatible with GNNs of different architectures. Extensive experiments on five benchmark datasets demonstrate our FreeKD outperforms two base GNNs in a large margin, and shows its efficacy to various GNNs. More surprisingly, our FreeKD has comparable or even better performance than traditional KD algorithms that distill knowledge from a deeper and stronger teacher GNN.