Zidi Xiong, Yuping Lin, Wenya Xie, Pengfei He, Zirui Liu, Jiliang Tang, Himabindu Lakkaraju, Zhen Xiang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

As the gap between processor and memory performance widens, optimizing data access performance becomes increasingly critical. Hardware prefetching is a widely used technique to hide long-latency off-chip memory accesses, but state-of-the-art prefetchers struggle with diverse and dynamic access patterns. Their limited adaptability leads to excessive storage overhead and reduced effectiveness under memory-intensive workloads. We propose Zion, a comprehensive, adaptive, and lightweight hardware prefetcher for memory-intensive workloads. At its core, Zion uses Independent Temporal-Spatial Modules (ITSM) for broad pattern coverage and runtime adaptability to diverse memory access patterns. Moreover, Zion leverages runtime feedback to dynamically guide prefetching decisions and maintain efficiency under memory pressure. Extensive multi-core evaluations show that Zion consistently outperforms state-of-the-art prefetchers, achieving up to 43.2% performance improvement on SPEC and 43.0% on self-attention workloads, while maintaining low overhead and broad effectiveness.

The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate. Currently, there is a lack of quantitative methods to evaluate the performance of LLMs in these low-resource languages. To address this gap, we propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using internal representations. By comparing the LLM's internal representation of various languages against a baseline derived from English, we can assess the model's multilingual capabilities in a robust and language-agnostic manner. Our analysis reveals that high-resource languages exhibit higher similarity scores with English, demonstrating superior performance, while low-resource languages show lower similarity scores, underscoring the effectiveness of our metric in assessing language-specific capabilities. Besides, the experiments show that there is a strong correlation between the LLM’s performance in different languages and the proportion of those languages in its pre-training corpus. These insights underscore the efficacy of the Language Ranker as a tool for evaluating LLM performance across different languages, particularly those with limited resources.

Densely structured pruning methods — which generate pruned models in a fully dense format, allowing immediate compression benefits without additional demands — are evolving due to their practical significance. Traditional techniques in this domain mainly revolve around coarser granularities, such as filter pruning, thereby limiting performance due to restricted pruning freedom. Recent advancements in Grouped Kernel Pruning (GKP) have enabled the utilization of finer granularities while maintaining a densely structured format. We observe that existing GKP methods often introduce dynamic operations to different aspects of their procedures at the cost of adding complications and/or imposing limitations (e.g., requiring an expensive mixture of clustering schemes), or contain dynamic pruning rates and sizes among groups that result in a reliance on custom architecture support for its pruned models. In this work, we argue that the best practice to introduce these dynamic operations to GKP is to make Conv2d(groups) (a.k.a. group count) flexible under an integral optimization, leveraging its ideal alignment with the infrastructure support of Grouped Convolution. Pursuing such a direction, we present a one-shot, post-train, data-agnostic GKP method that is more performant, adaptive, and efficient than its predecessors while simultaneously being user-friendly, with little-to-no hyper-parameter tuning or handcrafting of criteria required.

Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens.We show that a significant portion of these tokens are useless self-repetitions -what we call "word salad" -that exhaust the decoding budget without adding value.Interestingly, we observe that LRMs are self-aware when trapped in these loops: the hidden states of <\n\n> tokens trailing each reasoning chunk exhibit patterns that allow us to detect word salad behavior onthe-fly via a single-layer linear classifier.Once detected, a simple chop appended by a straightforward regeneration prompt yields substantial length savings with minimal quality loss.Our work offers WordSaladChopper (WSC) -a lightweight, turnkey component for LRM that is minimally invasive to its reasoning trajectory by only removing semantically redundant tokens.Given its low overhead, strong savings, and the lack of semantic value of word salad tokens, we believe it is not too far-fetched to argue that WSC -or a similar component -is a must-have for all LRM applications with user experience in mind.

Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language Models using only forward passes. However, applying ZO fine-tuning in memory-constrained settings such as mobile phones and laptops remains challenging since these settings often involve weight quantization, while ZO requires full-precision perturbation and update. In this study, we address this limitation by combining static sparse ZO fine-tuning with quantization. Our approach transfers a small, static subset (0.1%) of "sensitive" parameters from pre-training to downstream tasks, focusing fine-tuning on this sparse set of parameters. The remaining untuned parameters are quantized, reducing memory demands. Our proposed workflow enables efficient ZO fine-tuning of an Llama2-7B model on a GPU device with less than 8GB of memory while outperforming full model ZO fine-tuning performance and in-context learning.

Large language models (LLMs) have demonstrated significant potential in the development of intelligent LLM-based agents. However, when users use these agent applications to perform file operations, their interaction with the file system still remains the traditional paradigm: reliant on manual navigation through precise commands. This paradigm poses a bottleneck to the usability of these systems as users are required to navigate complex folder hierarchies and remember cryptic file names. To address this limitation, we propose an LLM-based Semantic File System (LSFS) for prompt-driven file management in LLM Agent Operating System (AIOS). Unlike conventional approaches, LSFS incorporates LLMs to enable users or agents to interact with files through natural language prompts, facilitating semantic file management. At the macro-level, we develop a comprehensive API set to achieve semantic file management functionalities, such as semantic file retrieval, file update summarization, and semantic file rollback). At the micro-level, we store files by constructing semantic indexes for them, design and implement syscalls of different semantic operations, e.g., CRUD (create, read, update, delete), group by, join. Our experiments show that LSFS can achieve at least 15% retrieval accuracy improvement with 2.1× higher retrieval speed in the semantic file retrieval task compared with the traditional file system. In the traditional keyword-based file retrieval task (i.e., retrieving by string-matching), LSFS also performs stably well, i.e., over 89% F1-score with improved usability, especially when the keyword conditions become more complex. Additionally, LSFS supports more advanced file management operations, i.e., semantic file rollback and file sharing and achieves 100% success rates in these tasks, further suggesting the capability of LSFS . The code is available at https://github.com/agiresearch/AIOS-LSFS.

Large language models (LLMs) have achieved remarkable success in contextual knowledge understanding. In this paper, we show for the first time that these concentrated massive values consistently emerge in specific regions of attention queries (Q) and keys (K) while not having such patterns in values (V) in various modern transformer-based LLMs. Through extensive experiments, we further demonstrate that these massive values play a critical role in interpreting contextual knowledge (i.e., knowledge obtained from the current context window) rather than in retrieving parametric knowledge stored within the model’s parameters. Our further investigation of quantization strategies reveals that ignoring these massive values leads to a pronounced drop in performance on tasks requiring rich contextual understanding, aligning with our analysis. Finally, we trace the emergence of concentrated massive values and find that such concentration is caused by Rotary Positional Encoding (RoPE) and it appears since very first layers. These findings shed new light on how Q and K operate in LLMs and offer practical insights for model design and optimization. The code is available at https://github.com/MingyuJ666/Rope_with_LLM.

Recent language models exhibit strong reasoning capabilities, yet the influence of long-context capacity on reasoning remains underexplored. In this work, we hypothesize that current limitations in reasoning stem, in part, from insufficient long-context capacity, motivated by empirical observations such as i) higher context window length often leads to stronger reasoning performance, and ii) failed reasoning cases resemble failed long-context cases. To test this hypothesis, we examine whether enhancing a model’s long-context ability before Supervised Fine-Tuning (SFT) leads to improved reasoning performance. Specifically, we compared models with identical architectures and fine-tuning data but varying levels of long-context capacity. Our results reveal a consistent trend: models with stronger long-context capacity achieve significantly higher accuracy on reasoning benchmarks after SFT. Notably, these gains persist even on tasks with short input lengths, indicating that long-context training offers generalizable benefits for reasoning performance. These findings suggest that long-context modeling is not just essential for processing lengthy inputs, but also serves as a critical foundation for reasoning. We advocate for treating long-context capacity as a first-class objective in the design of future language models.

Large Language Models (LLMs) are now integral across various domains and have demonstrated impressive performance. Progress, however, rests on the premise that benchmark scores are both accurate and reproducible. We demonstrate that the reproducibility of LLM performance is fragile: changing system configuration, such as evaluation batch size, GPU count, and GPU version, can introduce significant differences in the generated responses. This issue is especially pronounced in reasoning models, where minor rounding differences in early tokens can cascade into divergent chains of thought, ultimately affecting accuracy. For instance, under bfloat16 precision with greedy decoding, a reasoning model like DeepSeek-R1-Distill-Qwen-7B can exhibit up to 9\% variation in accuracy and 9,000 tokens difference in response length due to differences in GPU count, type, and evaluation batch size. We trace the root cause of this variability to the non-associative nature of floating-point arithmetic under limited numerical precision. This work presents the first systematic investigation into how numerical precision affects reproducibility in LLM inference. Through carefully controlled experiments across various hardware, software, and precision settings, we quantify when and how model outputs diverge. Our analysis reveals that floating-point precision—while critical for reproducibility—is often neglected in evaluation practices. Inspired by this, we develop a lightweight inference pipeline, dubbed LayerCast, that stores weights in 16-bit precision but performs all computations in FP32, balancing memory efficiency with numerical stability. Code is available at https://github.com/nanomaoli/llm_reproducibility.

Low-rank optimization has emerged as a promising approach to enabling memory-efficient training of large language models (LLMs). Existing low-rank optimization methods typically project gradients onto a low-rank subspace, reducing the memory cost of storing optimizer states. A key challenge in these methods is selecting suitable subspaces to ensure an effective optimization trajectory. Most existing approaches select the dominant subspace to preserve gradient information, as this intuitively provides the best approximation. However, we find that in practice, the dominant subspace stops changing during pretraining, thereby constraining weight updates to similar subspaces. In this paper, we propose importance sampling for low-rank optimization in LLM pretraining with a provable convergence guarantee, which the dominant subspace approach does not have. Empirically, we demonstrate that our method significantly outperforms previous methods in LLM pretraining tasks.

As Graph Neural Networks (GNNs) have been widely used in real-world applications, model explanations are required not only by users but also by legal regulations. However, simultaneously achieving high fidelity and low computational costs in generating explanations has been a challenge for current methods. In this work, we propose a framework of GNN explanation named L e A rn R emoval-based A ttribution (LARA) to address this problem. Specifically, we introduce removal-based attribution and demonstrate its substantiated link to interpretability fidelity theoretically and experimentally. The explainer in LARA learns to generate removal-based attribution which enables providing explanations with high fidelity. A strategy of subgraph sampling is designed in LARA to improve the scalability of the training process. In the deployment, LARA can efficiently generate the explanation through a feed-forward pass. We benchmark our approach with other state-of-the-art GNN explanation methods on six datasets. Results highlight the effectiveness of our framework regarding both efficiency and fidelity. In particular, LARA is 3.1 \(\times\) faster and achieves higher fidelity than the state-of-the-art method on the large dataset ogbn-arxiv (more than 160K nodes and 1M edges), showing its great potential in real-world applications. Our source code is available at https://github.com/yaorong0921/LARA .

There has been significant progress in improving the performance of graph neural networks (GNNs) through enhancements in graph data, model architecture design, and training strategies. For fairness in graphs, recent studies achieve fair representations and predictions through either graph data pre-processing (e.g., node feature masking, and topology rewiring) or fair training strategies (e.g., regularization, adversarial debiasing, and fair contrastive learning). How to achieve fairness in graphs from the model architecture perspective is less explored. More importantly, GNNs exhibit worse fairness performance compared to multilayer perception since their model architecture (i.e., neighbor aggregation) amplifies biases. To this end, we aim to achieve fairness via a new GNN architecture. We propose Fair Message Passing (FMP) designed within a unified optimization framework for GNNs. Notably, FMP explicitly renders sensitive attribute usage in forward propagation for node classification task using cross-entropy loss without data pre-processing. In FMP, the aggregation is first adopted to utilize neighbors' information and then the bias mitigation step explicitly pushes demographic group node presentation centers together. In this way, FMP scheme can aggregate useful information from neighbors and mitigate bias to achieve better fairness and prediction tradeoff performance. Experiments on node classification tasks demonstrate that the proposed FMP outperforms several baselines in terms of fairness and accuracy on three real-world datasets. The code is available at https://github.com/zhimengj0326/FMP.

Guanchu Wang, Yu-Neng Chuang, Ruixiang Tang, Shaochen Zhong, Jiayi Yuan, Hongye Jin, Zirui Liu, Vipin Chaudhary, Shuai Xu, James Caverlee, Xia Hu. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

It is well known that LLMs cannot generalize well to long contexts whose lengths are larger than the training sequence length. This poses challenges when employing LLMs for processing long input sequences during inference. In this work, we argue that LLMs themselves have inherent capabilities to handles s long contexts without fine-tuning. To achieve this goal, we propose SelfExtend to extend the context window of LLMs by constructing bi-level attention information: the grouped attention and the neighbor attention. The grouped attention captures the dependencies among tokens that are far apart, while neighbor attention captures dependencies among adjacent tokens within a specified range. The two-level attentions are computed based on the original model’s self-attention mechanism during inference. With minor code modification, our SelfExtend can effortlessly extend existing LLMs’ context window without any fine-tuning. We conduct comprehensive experiments on multiple benchmarks and the results show that our SelfExtend can effectively extend existing LLMs’ context window length.

Knowledge Graphs (KGs) are potent frameworks for knowledge representation and reasoning. Nevertheless, KGs are inherently incomplete, leaving numerous uncharted relationships and facts awaiting discovery. Deep learning methodologies have proven effective in enhancing KG completion by framing it as a link prediction task, where the goal is to discern the validity of a triple comprising a head, relation, and tail. The significance of structural information in assessing the validity of a triple within a KG is well-established. However, quantifying this structural information poses a challenge. We need to pinpoint the metric that encapsulates the structural information of a triple and smoothly incorporate this metric into the link prediction learning process. In this study, we recognize the critical importance of the intersection among the $k$-hop neighborhoods of the head, relation, and tail when determining the validity of a triple. To address this, we introduce a novel randomized algorithm designed to efficiently generate intersection features for candidate triples. Our experimental results demonstrate that a straightforward fully-connected network leveraging these intersection features can surpass the performance of established KG embedding models and even outperform graph neural network baselines. Additionally, we highlight the substantial training time efficiency gains achieved by our network trained on intersection features.

Efficiently serving large language models (LLMs) requires batching many requests together to reduce the cost per request. Yet, the key-value (KV) cache, which stores attention keys and values to avoid re-computations, significantly increases memory demands and becomes the new bottleneck in speed and memory usage. This memory demand increases with larger batch sizes and longer context lengths. Additionally, the inference speed is limited by the size of KV cache, as the GPU's SRAM must load the entire KV cache from the main GPU memory for each token generated, causing the computational core to be idle during this process. A straightforward and effective solution to reduce KV cache size is quantization, which decreases the total bytes taken by KV cache. However, there is a lack of in-depth studies that explore the element distribution of KV cache to understand the hardness and limitation of KV cache quantization. To fill the gap, we conducted a comprehensive study on the element distribution in KV cache of popular LLMs. Our findings indicate that the key cache should be quantized per-channel, i.e., group elements along the channel dimension and quantize them together. In contrast, the value cache should be quantized per-token. From this analysis, we developed a tuning-free 2bit KV cache quantization algorithm, named KIVI. With the hardware-friendly implementation, KIVI can enable Llama (Llama-2), Falcon, and Mistral models to maintain almost the same quality while using 2.6$\times$ less peak memory usage (including the model weight). This reduction in memory usage enables up to 4x larger batch size, bringing $2.35 \times \sim 3.47 \times$ throughput on real LLM inference workload.

Explainable machine learning significantly improves the transparency of deep neural networks. However, existing work is constrained to explaining the behavior of individual model predictions, and lacks the ability to transfer the explanation across various models and tasks. This limitation results in explaining various tasks being time- and resource-consuming. To address this problem, we introduce a Transferable Vision Explainer (TVE) that can effectively explain various vision models in downstream tasks. Specifically, the transferability of TVE is realized through a pre-training process on large-scale datasets towards learning the meta-attribution. This meta-attribution leverages the versatility of generic backbone encoders to comprehensively encode the attribution knowledge for the input instance, which enables TVE to seamlessly transfer to explaining various downstream tasks, without the need for training on task-specific data. Empirical studies involve explaining three different architectures of vision models across three diverse downstream datasets. The experiment results indicate TVE is effective in explaining these tasks without the need for additional training on downstream data.

Model compression is one of the most popular approaches to improve the accessibility of Large Language Models (LLMs) by reducing their memory footprint. However, the gaining of such efficiency benefits often simultaneously demands extensive engineering efforts and intricate designs to mitigate the performance decline. In this work, we leverage *(Soft) Prompt Tuning* in its most vanilla form and discover such conventionally learned soft prompts can recover the performance of compressed LLMs. More surprisingly, we observe such recovery effect to be transferable among different tasks and models (albeit natural tokenizer and dimensionality limitations), resulting in further overhead reduction and yet, subverting the common belief that learned soft prompts are task-specific. Our work is fully orthogonal and compatible with model compression frameworks such as pruning and quantization, where we enable up to $8\times$ compressed LLM (with a joint 4-bit quantization and 50% weight pruning compression) to match its uncompressed counterparts on popular benchmarks. We note that we are the first to reveal vanilla Parameter-Efficient Fine-Tuning (PEFT) techniques have the potential to be utilized under a compression recovery context, opening a new line of opportunities for model accessibility advancement while freeing our fellow researchers from the previously present engineering burdens and constraints. The code is available at https://github.com/zirui-ray-liu/compress-then-prompt.

Suppose a self-driving car is crashing into pedestrians, or a chatbot is instructing its users to conduct criminal wrongdoing; the stakeholders of such products will undoubtedly want to patch these catastrophic errors as soon as possible. To address such concerns, Model Editing: the study of efficiently patching model behaviors without significantly altering their general performance, has seen considerable activity, with hundreds of editing techniques developed in various domains such as CV and NLP. However, the graph learning community has objectively fallen behind with only a few Graph Neural Network-compatible — and just one GNN-specific — model editing methods available, where all of which are limited in their practical scope. We argue that the impracticality of these methods lies in their lack of Sequential Editing Robustness: the ability to edit multiple errors sequentially, and therefore fall short in effectiveness, as this approach mirrors how errors are discovered and addressed in the real world. In this paper, we delve into the specific reasons behind the difficulty of editing GNNs in succession and observe the root cause to be model overfitting. We subsequently propose a simple yet effective solution — SEED-GNN — by leveraging overfit-prevention techniques in a GNN-specific context to derive the first and only GNN model editing method that scales practically. Additionally, we formally frame the task paradigm of GNN editing and hope to inspire future research in this crucial but currently overlooked field. Please refer to our GitHub repository for code and checkpoints.

Yu-Neng Chuang, Tianwei Xing, Chia-Yuan Chang, Zirui Liu, Xun Chen, Xia Hu. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Deep neural networks are ubiquitously adopted in many applications, such as computer vision, natural language processing, and graph analytics. However, well-trained neural networks can make prediction errors after deployment as the world changes. \textit{Model editing} involves updating the base model to correct prediction errors with less accessible training data and computational resources. Despite recent advances in model editors in computer vision and natural language processing, editable training in graph neural networks (GNNs) is rarely explored. The challenge with editable GNN training lies in the inherent information aggregation across neighbors, which can lead model editors to affect the predictions of other nodes unintentionally. In this paper, we first observe the gradient of cross-entropy loss for the target node and training nodes with significant inconsistency, which indicates that directly fine-tuning the base model using the loss on the target node deteriorates the performance on training nodes. Motivated by the gradient inconsistency observation, we propose a simple yet effective \underline{G}radient \underline{R}ewiring method for \underline{E}ditable graph neural network training, named \textbf{GRE}. Specifically, we first store the anchor gradient of the loss on training nodes to preserve the locality. Subsequently, we rewire the gradient of the loss on the target node to preserve performance on the training node using anchor gradient. Experiments demonstrate the effectiveness of GRE on various model architectures and graph datasets in terms of multiple editing situations. The source code is available at \url{https://github.com/zhimengj0326/Gradient_rewiring_editing}.

Training graph neural networks (GNNs) is extremely time consuming because sparse graph-based operations are hard to be accelerated by community hardware. Prior art successfully reduces the computation cost of dense matrix based operations (e.g., convolution and linear) via sampling-based approximation. However, unlike dense matrices, sparse matrices are stored in the irregular data format such that each row/column may have different number of non-zero entries. Thus, compared to the dense counterpart, approximating sparse operations has two unique challenges (1) we cannot directly control the efficiency of approximated sparse operation since the computation is only executed on non-zero entries; (2) sampling sparse matrices is much more inefficient due to the irregular data format. To address the issues, our key idea is to control the accuracy-efficiency trade off by optimizing computation resource allocation layer-wisely and epoch-wisely. For the first challenge, we customize the computation resource to different sparse operations, while limit the total used resource below a certain budget. For the second challenge, we cache previous sampled sparse matrices to reduce the epoch-wise sampling overhead. Finally, we propose a switching mechanisms to improve the generalization of GNNs trained with approximated operations. To this end, we propose Randomized Sparse Computation. In practice, rsc can achieve up to 11.6X speedup for a single sparse operation and 1.6X end-to-end wall-clock time speedup with almost no accuracy drop.

Activation compressed training provides a solution towards reducing the memory cost of training deep neural networks (DNNs). However, state-of-the-art work combines a search of quantization bit-width with the training, which makes the procedure complicated and less transparent. To this end, we propose a simple and effective method to compress DNN training. Our method is motivated by an instructive observation: DNN backward propagation mainly utilizes the low-frequency component (LFC) of the activation maps, while the majority of memory is for caching the high-frequency component (HFC) during the training. This indicates the HFC of activation maps is highly redundant and compressible, which inspires our proposed Dual Activation Precision (DIVISION). During the training, DIVISION preserves a high-precision copy of LFC and compresses the HFC into a light-weight copy with low numerical precision. This can significantly reduce the memory cost while maintaining a competitive model accuracy. Experiment results show DIVISION has better comprehensive performance than state-of-the-art methods, including over 10x compression of activation maps and competitive training throughput, without loss of model accuracy. The source code is available at https://github.com/guanchuwang/division.

As the model size grows rapidly, fine-tuning the large pre-trained language model has become increasingly difficult due to its extensive memory usage. Previous works usually focus on reducing the number of trainable parameters in the network. While the model parameters do contribute to memory usage, the primary memory bottleneck during training arises from storing feature maps, also known as activations, as they are crucial for gradient calculation. Notably, machine learning models are typically trained using stochastic gradient descent. We argue that in stochastic optimization, models can handle noisy gradients as long as the gradient estimator is unbiased with reasonable variance. Following this motivation, we propose a new family of unbiased estimators called \sas, for matrix production with reduced variance, which only requires storing the sub-sampled activations for calculating the gradient. Our work provides both theoretical and experimental evidence that, in the context of tuning transformers, our proposed estimators exhibit lower variance compared to existing ones. By replacing the linear operation with our approximated one in transformers, we can achieve up to 2.7X peak memory reduction with almost no accuracy drop and enables up to $6.4\times$ larger batch size. Under the same hardware, \sas enables better down-streaming task performance by applying larger models and/or faster training speed with larger batch sizes. The code is available at https://anonymous.4open.science/r/WTACRS-A5C5/.

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the adversaries can embed malicious prediction behaviors by manipulating a few training samples. In this study, our objective is to develop a backdoor-resistant tuning procedure that yields a backdoor-free model, no matter whether the fine-tuning dataset contains poisoned samples. To this end, we propose and integrate an \emph{honeypot module} into the original PLM, specifically designed to absorb backdoor information exclusively. Our design is motivated by the observation that lower-layer representations in PLMs carry sufficient backdoor features while carrying minimal information about the original tasks. Consequently, we can impose penalties on the information acquired by the honeypot module to inhibit backdoor creation during the fine-tuning process of the stem network. Comprehensive experiments conducted on benchmark datasets substantiate the effectiveness and robustness of our defensive strategy. Notably, these results indicate a substantial reduction in the attack success rate ranging from 10\% to 40\% when compared to prior state-of-the-art methods.

Densely structured pruning methods utilizing simple pruning heuristics can deliver immediate compression and acceleration benefits with acceptable benign performances. However, empirical findings indicate such naively pruned networks are extremely fragile under simple adversarial attacks. Naturally, we would be interested in knowing if such a phenomenon also holds for carefully designed modern structured pruning methods. If so, then to what extent is the severity? And what kind of remedies are available? Unfortunately, both the questions and the solution remain largely unaddressed: no prior art is able to provide a thorough investigation on the adversarial performance of modern structured pruning methods (spoiler: it is not good), yet the few works that attempt to provide mitigation often do so at various extra costs with only to-be-desired performance. In this work, we answer both questions by fairly and comprehensively investigating the adversarial performance of 10+ popular structured pruning methods. Solution-wise, we take advantage of *Grouped Kernel Pruning (GKP)*'s recent success in pushing densely structured pruning freedom to a more fine-grained level. By mixing up kernel smoothness — a classic robustness-related kernel-level metric — into a modified GKP procedure, we present a one-shot-post-train-weight-dependent GKP method capable of advancing SOTA performance on both the benign and adversarial scale, while requiring no extra (in fact, often less) cost than a standard pruning procedure. Please refer to our [GitHub repository](https://github.com/henryzhongsc/adv_robust_gkp) for code implementation, tool sharing, and model checkpoints.

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains. To handle large-scale graphs, most of the existing methods partition the input graph into multiple sub-graphs (e.g., through node clustering) and apply batch training to save memory cost. However, such batch training will lead to label bias within each batch and result in over- confidence in model predictions. Since the connected nodes with positively related labels tend to be assigned together, the traditional cross-entropy minimization process attends on the predictions of biased classes at a batch to intensify the overfitting issue. To overcome the problem of label bias, we propose adaptive label smoothing (ALS) method to replace the one-hot hard labels with smoothed ones, which learns to allocate label confidences from the biased classes to the others. Specifically, ALS propagates node labels to aggregate the neighborhood label distribution in a pre-processing step, and then updates the optimal smoothed labels online to adapt to specific graph structure. Experiments on the real-world datasets demonstrate that ALS can be generally applied to the main scalable learning frameworks to calibrate the biased labels and improve generalization performances.

Learning useful interactions between input features is crucial for tabular data modeling. Recent efforts start to explicitly model the feature interactions with graph, where each feature is treated as an individual node. However, the existing graph construction methods either heuristically formulate a fixed feature-interaction graph based on specific domain knowledge, or simply apply attention function to compute the pairwise feature similarities for each sample. While the fixed graph may be sub-optimal to downstream tasks, the sample-wise graph construction is time-consuming during model training and inference. To tackle these issues, we propose a framework named Table2Graph to transform the feature interaction modeling to learning a unified graph. Represented as a probability adjacency matrix, the unified graph learns to model the key feature interactions shared by the diverse samples in the tabular data. To well optimize the unified graph, we employ the reinforcement learning policy to capture the key feature interactions stably. A sparsity constraint is also proposed to regularize the learned graph from being overly-sparse/smooth. The experimental results in a variety of real-world applications demonstrate the effectiveness and efficiency of our Table2Graph, in terms of the prediction accuracy and feature interaction detection.

Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs). Due to the nature of evolving graph structures into the training process, vanilla GNNs usually fail to scale up, limited by the GPU memory space. Up to now, though numerous scalable GNN architectures have been proposed, we still lack a comprehensive survey and fair benchmark of this reservoir to find the rationale for designing scalable GNNs. To this end, we first systematically formulate the representative methods of large-scale graph training into several branches and further establish a fair and consistent benchmark for them by a greedy hyperparameter searching. In addition, regarding efficiency, we theoretically evaluate the time and space complexity of various branches and empirically compare them w.r.t GPU memory usage, throughput, and convergence. Furthermore, We analyze the pros and cons for various branches of scalable GNNs and then present a new ensembling training manner, named EnGCN, to address the existing issues. Remarkably, our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets. Our code is available at https://github.com/VITA-Group/LargeScaleGCN_Benchmarking.

We study embedding table placement for distributed recommender systems, which aims to partition and place the tables on multiple hardware devices (e.g., GPUs) to balance the computation and communication costs. Although prior work has explored learning-based approaches for the device placement of computational graphs, embedding table placement remains to be a challenging problem because of 1) the operation fusion of embedding tables, and 2) the generalizability requirement on unseen placement tasks with different numbers of tables and/or devices. To this end, we present DreamShard, a reinforcement learning (RL) approach for embedding table placement. DreamShard achieves the reasoning of operation fusion and generalizability with 1) a cost network to directly predict the costs of the fused operation, and 2) a policy network that is efficiently trained on an estimated Markov decision process (MDP) without real GPU execution, where the states and the rewards are estimated with the cost network. Equipped with sum and max representation reductions, the two networks can directly generalize to any unseen tasks with different numbers of tables and/or devices without fine-tuning. Extensive experiments show that DreamShard substantially outperforms the existing human expert and RNN-based strategies with up to 19% speedup over the strongest baseline on large-scale synthetic tables and our production tables. The code is available.

Human-designed data augmentation strategies have been replaced by automatically learned augmentation policy in the past two years. Specifically, recent work has empirically shown that the superior performance of the automated data augmentation methods stems from increasing the diversity of augmented data [4], [5]. However, two factors regarding the diversity of augmented data are still missing: 1) the explicit definition (and thus measurement) of diversity and 2) the quantifiable relationship between diversity and its regularization effects. To bridge this gap, we propose a diversity measure called Variance Diversity and theoretically show that the regularization effect of data augmentation is promised by Variance Diversity. We validate in experiments that the relative gain from automated data augmentation in test accuracy is highly correlated to Variance Diversity. An unsupervised sampling-based framework, DivAug, is designed to directly maximize Variance Diversity and hence strengthen the regularization effect. Without requiring a separate search process, the performance gain from DivAug is comparable with the state-of-the-art method with better efficiency. Moreover, under the semi-supervised setting, our framework can further improve the performance of semi-supervised learning algorithms compared to RandAugment, making it highly applicable to real-world problems, where labeled data is scarce. The code is available at https://github.com/warai-0toko/DivAug.

Image captioning has made substantial progress with huge supporting image collections sourced from the web. However, recent studies have pointed out that captioning datasets, such as COCO, contain gender bias found in web corpora. As a result, learning models could heavily rely on the learned priors and image context for gender identification, leading to incorrect or even offensive errors. To encourage models to learn correct gender features, we reorganize the COCO dataset and present two new splits COCO-GB V1 and V2 datasets where the train and test sets have different gender-context joint distribution. Models relying on contextual cues will suffer from huge gender prediction errors on the anti-stereotypical test data. Benchmarking experiments reveal that most captioning models learn gender bias, leading to high gender prediction errors, especially for women. To alleviate the unwanted bias, we propose a new Guided Attention Image Captioning model (GAIC) which provides self-guidance on visual attention to encourage the model to capture correct gender visual evidence. Experimental results validate that GAIC can significantly reduce gender prediction errors with a competitive caption quality. Our codes and the designed benchmark datasets are available at https://github.com/datamllab/Mitigating_Gender_Bias_In_Captioning_System.

Detecting statistical interactions between input features is a crucial and challenging task. Recent advances demonstrate that it is possible to extract learned interactions from trained neural networks. It has also been observed that, in neural networks, any interacting features must follow a strongly weighted connection to common hidden units. Motivated by the observation, in this paper, we propose to investigate the interaction detection problem from a novel topological perspective by analyzing the connectivity in neural networks. Specially, we propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. Based on this measure, a Persistence Interaction Dection (PID) algorithm is developed to efficiently detect interactions. Our proposed algorithm is evaluated across a number of interaction detection tasks on several synthetic and real-world datasets with different hyperparameters. Experimental results validate that the PID algorithm outperforms the state-of-the-art baselines.

Realistic recommender systems are often required to adapt to ever-changing data and tasks or to explore different models systematically. To address the need, we present AutoRec 1 2, an open-source automated machine learning (AutoML) platform extended from the TensorFlow [3] ecosystem and, to our knowledge, the first framework to leverage AutoML for model search and hyperparameter tuning in deep recommendation models. AutoRec also supports a highly flexible pipeline that accommodates both sparse and dense inputs, rating prediction and click-through rate (CTR) prediction tasks, and an array of recommendation models. Lastly, AutoRec provides a simple, user-friendly API. Experiments conducted on the benchmark datasets reveal AutoRec is reliable and can identify models which resemble the best model without prior knowledge.

This paper proposes a novel on-line algorithm to obtain knowledge of moment of inertia by iteratively computing. Since load torque and moment of inertia are variables which cannot be decoupled, so it is hard to achieve good performance when load torque varies. This paper eliminates this problem and realizes ideal online inertia identification regardless of load condition. The algorithm in this paper introduces adaptive controllers to Recursive Least Squares to enhance its robustness. A Kalman Filter is employed to obtain a more accurate value of inertia. It has better performance during iteratively load torque computation and moment of inertia. Compared with traditional method, the validity of the proposed algorithm is proved by simulation and experiment results.