arXiv subjects

Shwai He

Publications and source records attributed to Shwai He.

33 records · Page 2Linked to original sources

arXiv2024

Loki: Low-rank Keys for Efficient Sparse Attention

Inference on large language models (LLMs) can be expensive in terms of the compute and memory costs involved, especially when long sequence lengths are used. In particular, the self-attention mechanism used in LLM inference contributes significantly to these costs, which has sparked an interest in approximating the self-attention computation to reduce such costs. In this work, we propose to approximate self-attention by focusing on the dimensionality of key vectors computed in the attention block. Our analysis reveals that key vectors lie in a significantly lower-dimensional space, consistently across several datasets and models. Exploiting this observation, we propose Loki, a novel sparse attention method that ranks and selects tokens in the KV-cache based on attention scores computed in low-dimensional space. Our evaluations show that Loki is able to speed up the attention computation due to reduced data movement (load/store) and compute costs while maintaining the efficacy of the models better than other popular approximation methods.

cs.LG↗

arXiv2024

What Matters in Transformers? Not All Attention is Needed

While scaling Transformer-based large language models (LLMs) has demonstrated promising performance across various tasks, it also introduces redundant architectures, posing efficiency challenges for real-world deployment. Despite some recognition of redundancy in LLMs, the variability of redundancy across different architectures in transformers, such as MLP and Attention layers, is under-explored. In this work, we investigate redundancy across different modules within Transformers, including Blocks, MLP, and Attention layers, using a similarity-based metric. Surprisingly, despite the critical role of attention layers in distinguishing transformers from other architectures, we found that a large portion of these layers exhibit excessively high similarity and can be pruned without degrading performance. For instance, Llama-2-70B achieved a 48.4\% speedup with only a 2.4\% performance drop by pruning half of the attention layers. Furthermore, by tracing model checkpoints throughout the training process, we observed that attention layer redundancy is inherent and consistent across training stages. Additionally, we further propose a method that jointly drops Attention and MLP layers, allowing us to more aggressively drop additional layers. For instance, when dropping 31 layers (Attention + MLP), Llama-2-13B still retains 90\% of the performance on the MMLU task. Our work provides valuable insights for future network architecture design. The code is released at: \url{https://github.com/Shwai-He/LLM-Drop}.

cs.LG↗

arXiv2024

Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration

Vision-Language Models (VLMs) integrate information from multiple modalities and have shown remarkable success across various tasks. However, deploying large-scale VLMs in resource-constrained scenarios is challenging. Pruning followed by finetuning offers a potential solution but remains underexplored for VLMs. This study addresses two key questions: how to distribute sparsity across different modality-specific models, and how to restore the performance of pruned sparse VLMs. Our preliminary studies identified two effective pruning settings: applying the same sparsity to both vision and language models, and pruning only the language models. While LoRA finetuning aims to restore sparse models, it faces challenges due to incompatibility with sparse models, disrupting the pruned sparsity. To overcome these issues, we propose SparseLoRA, which applies sparsity directly to LoRA weights. Our experimental results demonstrate significant improvements, including an 11.3\% boost under 2:4 sparsity and a 47.6\% enhancement under unstructured 70\% sparsity. Code is released at: \url{https://github.com/Shwai-He/VLM-Compression}.

cs.LG↗

arXiv2024

Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But it also leads to extra cost and computation due to the involvement of LLMs in this process. To reduce the filtering cost, we study Superfiltering: Can we use a smaller and weaker model to select data for finetuning a larger and stronger model? Despite the performance gap between weak and strong language models, we find their highly consistent capability to perceive instruction difficulty and data selection results. This enables us to use a much smaller and more efficient model to filter the instruction data used to train a larger language model. Not only does it largely speed up the data filtering, but the filtered-data-finetuned LLM achieves even better performance on standard benchmarks. Extensive experiments validate the efficacy and efficiency of our approach.

cs.CL↗

arXiv2024

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Instruction tuning is critical to large language models (LLMs) for achieving better instruction following and task adaptation capabilities but its success heavily relies on the training data quality. Many recent methods focus on improving the data quality but often overlook the compatibility of the data with the student model being finetuned. This paper introduces Selective Reflection-Tuning, a novel paradigm that synergizes a teacher LLM's reflection and introspection for improving existing data quality with the data selection capability of the student LLM, to automatically refine existing instruction-tuning data. This teacher-student collaboration produces high-quality and student-compatible instruction-response pairs, resulting in sample-efficient instruction tuning and LLMs of superior performance. Selective Reflection-Tuning is a data augmentation and synthesis that generally improves LLM finetuning and self-improvement without collecting brand-new data. We apply our method to Alpaca and WizardLM data and achieve much stronger and top-tier 7B and 13B LLMs.

cs.CL↗

arXiv2024

Reformatted Alignment

The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone to factual errors caused by LLM hallucinations. This paper explores elevating the quality of existing instruction data to better align with human values, introducing a simple and effective approach named ReAlign, which reformats the responses of instruction data into a format that better aligns with pre-established criteria and the collated evidence. This approach minimizes human annotation, hallucination, and the difficulty in scaling, remaining orthogonal to existing alignment techniques. Experimentally, ReAlign significantly boosts the general alignment ability, math reasoning, factuality, and readability of the LLMs. Encouragingly, without introducing any additional data or advanced training techniques, and merely by reformatting the response, LLaMA-2-13B's mathematical reasoning ability on GSM8K can be improved from 46.77% to 56.63% in accuracy. Additionally, a mere 5% of ReAlign data yields a 67% boost in general alignment ability measured by the Alpaca dataset. This work highlights the need for further research into the science and mechanistic interpretability of LLMs. We have made the associated code and data publicly accessible to support future studies at https://github.com/GAIR-NLP/ReAlign.

cs.CL↗

arXiv2023

Merging Experts into One: Improving Computational Efficiency of Mixture of Experts

Scaling the size of language models usually leads to remarkable advancements in NLP tasks. But it often comes with a price of growing computational cost. Although a sparse Mixture of Experts (MoE) can reduce the cost by activating a small subset of parameters (e.g., one expert) for each input, its computation escalates significantly if increasing the number of activated experts, limiting its practical utility. Can we retain the advantages of adding more experts without substantially increasing the computational costs? In this paper, we first demonstrate the superiority of selecting multiple experts and then propose a computation-efficient approach called \textbf{\texttt{Merging Experts into One}} (MEO), which reduces the computation cost to that of a single expert. Extensive experiments show that MEO significantly improves computational efficiency, e.g., FLOPS drops from 72.0G of vanilla MoE to 28.6G (MEO). Moreover, we propose a token-level attention block that further enhances the efficiency and performance of token-level MEO, e.g., 83.3\% (MEO) vs. 82.6\% (vanilla MoE) average score on the GLUE benchmark. Our code will be released upon acceptance. Code will be released at: \url{https://github.com/Shwai-He/MEO}.

cs.CL↗

arXiv2023

Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning

Recent advancements in Large Language Models (LLMs) have expanded the horizons of natural language understanding and generation. Notably, the output control and alignment with the input of LLMs can be refined through instruction tuning. However, as highlighted in several studies, low-quality data in the training set are usually detrimental to instruction tuning, resulting in inconsistent or even misleading LLM outputs. We propose a novel method, termed "reflection-tuning," which addresses the problem by self-improvement and judging capabilities of LLMs. This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data. Extensive experiments on widely used evaluation benchmarks show that LLMs trained with our recycled data outperform those trained with existing datasets in various benchmarks.

cs.CL↗

arXiv2023

Accurate Prediction of Antibody Function and Structure Using Bio-Inspired Antibody Language Model

In recent decades, antibodies have emerged as indispensable therapeutics for combating diseases, particularly viral infections. However, their development has been hindered by limited structural information and labor-intensive engineering processes. Fortunately, significant advancements in deep learning methods have facilitated the precise prediction of protein structure and function by leveraging co-evolution information from homologous proteins. Despite these advances, predicting the conformation of antibodies remains challenging due to their unique evolution and the high flexibility of their antigen-binding regions. Here, to address this challenge, we present the Bio-inspired Antibody Language Model (BALM). This model is trained on a vast dataset comprising 336 million 40% non-redundant unlabeled antibody sequences, capturing both unique and conserved properties specific to antibodies. Notably, BALM showcases exceptional performance across four antigen-binding prediction tasks. Moreover, we introduce BALMFold, an end-to-end method derived from BALM, capable of swiftly predicting full atomic antibody structures from individual sequences. Remarkably, BALMFold outperforms those well-established methods like AlphaFold2, IgFold, ESMFold, and OmegaFold in the antibody benchmark, demonstrating significant potential to advance innovative engineering and streamline therapeutic antibody development by reducing the need for unnecessary trials.

q-bio.BM↗

arXiv2023

MerA: Merging Pretrained Adapters For Few-Shot Learning

Adapter tuning, which updates only a few parameters, has become a mainstream method for fine-tuning pretrained language models to downstream tasks. However, it often yields subpar results in few-shot learning. AdapterFusion, which assembles pretrained adapters using composition layers tailored to specific tasks, is a possible solution but significantly increases trainable parameters and deployment costs. Despite this, our preliminary study reveals that even single adapters can outperform Adapterfusion in few-shot learning, urging us to propose \textbf{\texttt{Merging Pretrained Adapters}} (MerA) that efficiently incorporates pretrained adapters to a single model through model fusion. Extensive experiments on two PLMs demonstrate that MerA achieves substantial improvements compared to both single adapters and AdapterFusion. To further enhance the capacity of MerA, we also introduce a simple yet effective technique, referred to as the "\textit{same-track}" setting, that merges adapters from the same track of pretraining tasks. With the implementation of the "\textit{same-track}" setting, we observe even more impressive gains, surpassing the performance of both full fine-tuning and adapter tuning by a substantial margin, e.g., 3.5\% in MRPC and 5.0\% in MNLI.

cs.CL↗

arXiv2023

PAD-Net: An Efficient Framework for Dynamic Networks

Dynamic networks, e.g., Dynamic Convolution (DY-Conv) and the Mixture of Experts (MoE), have been extensively explored as they can considerably improve the model's representation power with acceptable computational cost. The common practice in implementing dynamic networks is to convert the given static layers into fully dynamic ones where all parameters are dynamic (at least within a single layer) and vary with the input. However, such a fully dynamic setting may cause redundant parameters and high deployment costs, limiting the applicability of dynamic networks to a broader range of tasks and models. The main contributions of our work are challenging the basic commonsense in dynamic networks and proposing a partially dynamic network, namely PAD-Net, to transform the redundant dynamic parameters into static ones. Also, we further design Iterative Mode Partition to partition dynamic and static parameters efficiently. Our method is comprehensively supported by large-scale experiments with two typical advanced dynamic architectures, i.e., DY-Conv and MoE, on both image classification and GLUE benchmarks. Encouragingly, we surpass the fully dynamic networks by $+0.7\%$ top-1 acc with only $30\%$ dynamic parameters for ResNet-50 and $+1.9\%$ average score in language understanding with only $50\%$ dynamic parameters for BERT. Code will be released at: \url{https://github.com/Shwai-He/PAD-Net}.

cs.LG↗

arXiv2023

SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution

Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible FLOPs increase. However, the performance increase can not match the significantly expanded number of parameters, which is the main bottleneck in real-world applications. Contrastively, mask-based unstructured pruning obtains a lightweight network by removing redundancy in the heavy network. In this paper, we propose a new framework, \textbf{Sparse Dynamic Convolution} (\textsc{SD-Conv}), to naturally integrate these two paths such that it can inherit the advantage of dynamic mechanism and sparsity. We first design a binary mask derived from a learnable threshold to prune static kernels, significantly reducing the parameters and computational cost but achieving higher performance in Imagenet-1K. We further transfer pretrained models into a variety of downstream tasks, showing consistently better results than baselines. We hope our SD-Conv could be an efficient alternative to conventional dynamic convolutions.

cs.CV↗

arXiv2023

Vega-MT: The JD Explore Academy Translation System for WMT22

We describe the JD Explore Academy's submission of the WMT 2022 shared general translation task. We participated in all high-resource tracks and one medium-resource track, including Chinese-English, German-English, Czech-English, Russian-English, and Japanese-English. We push the limit of our previous work -- bidirectional training for translation by scaling up two main factors, i.e. language pairs and model sizes, namely the \textbf{Vega-MT} system. As for language pairs, we scale the "bidirectional" up to the "multidirectional" settings, covering all participating languages, to exploit the common knowledge across languages, and transfer them to the downstream bilingual tasks. As for model sizes, we scale the Transformer-Big up to the extremely large model that owns nearly 4.7 Billion parameters, to fully enhance the model capacity for our Vega-MT. Also, we adopt the data augmentation strategies, e.g. cycle translation for monolingual data, and bidirectional self-training for bilingual and monolingual data, to comprehensively exploit the bilingual and monolingual data. To adapt our Vega-MT to the general domain test set, generalization tuning is designed. Based on the official automatic scores of constrained systems, in terms of the sacreBLEU shown in Figure-1, we got the 1st place on {Zh-En (33.5), En-Zh (49.7), De-En (33.7), En-De (37.8), Cs-En (54.9), En-Cs (41.4) and En-Ru (32.7)}, 2nd place on {Ru-En (45.1) and Ja-En (25.6)}, and 3rd place on {En-Ja(41.5)}, respectively; W.R.T the COMET, we got the 1st place on {Zh-En (45.1), En-Zh (61.7), De-En (58.0), En-De (63.2), Cs-En (74.7), Ru-En (64.9), En-Ru (69.6) and En-Ja (65.1)}, 2nd place on {En-Cs (95.3) and Ja-En (40.6)}, respectively.

cs.CL↗

arXiv2022

SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters

Adapter Tuning, which freezes the pretrained language models (PLMs) and only fine-tunes a few extra modules, becomes an appealing efficient alternative to the full model fine-tuning. Although computationally efficient, the recent Adapters often increase parameters (e.g. bottleneck dimension) for matching the performance of full model fine-tuning, which we argue goes against their original intention. In this work, we re-examine the parameter-efficiency of Adapters through the lens of network pruning (we name such plug-in concept as \texttt{SparseAdapter}) and find that SparseAdapter can achieve comparable or better performance than standard Adapters when the sparse ratio reaches up to 80\%. Based on our findings, we introduce an easy but effective setting ``\textit{Large-Sparse}'' to improve the model capacity of Adapters under the same parameter budget. Experiments on five competitive Adapters upon three advanced PLMs show that with proper sparse method (e.g. SNIP) and ratio (e.g. 40\%) SparseAdapter can consistently outperform their corresponding counterpart. Encouragingly, with the \textit{Large-Sparse} setting, we can obtain further appealing gains, even outperforming the full fine-tuning by a large margin. Our code will be released at: https://github.com/Shwai-He/SparseAdapter.

cs.CL↗

arXiv2022

Multi-modal Attention Network for Stock Movements Prediction

Stock prices move as piece-wise trending fluctuation rather than a purely random walk. Traditionally, the prediction of future stock movements is based on the historical trading record. Nowadays, with the development of social media, many active participants in the market choose to publicize their strategies, which provides a window to glimpse over the whole market's attitude towards future movements by extracting the semantics behind social media. However, social media contains conflicting information and cannot replace historical records completely. In this work, we propose a multi-modality attention network to reduce conflicts and integrate semantic and numeric features to predict future stock movements comprehensively. Specifically, we first extract semantic information from social media and estimate their credibility based on posters' identity and public reputation. Then we incorporate the semantic from online posts and numeric features from historical records to make the trading strategy. Experimental results show that our approach outperforms previous methods by a significant margin in both prediction accuracy (61.20\%) and trading profits (9.13\%). It demonstrates that our method improves the performance of stock movements prediction and informs future research on multi-modality fusion towards stock prediction.

cs.LG↗