Linear Attention via Orthogonal Memory

• URL: http://arxiv.org/abs/2312.11135v1
• Date: Mon, 18 Dec 2023 12:26:27 GMT
• Title: Linear Attention via Orthogonal Memory
• Authors: Jun Zhang, Shuyang Jiang, Jiangtao Feng, Lin Zheng, Lingpeng Kong
• Abstract summary: We propose textbfLinear textbfAttention textbfVia textbfOrthogonal memory(shortname) to address these limitations. shortname achieves strong performance while maintaining linear complexity.
• Score: 46.14195464583495
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Efficient attentions have greatly improved the computational efficiency of Transformers. However, most existing linear attention mechanisms suffer from an \emph{efficiency degradation} problem, leading to inefficiencies in causal language modeling and hindering their application in long-range language models. This problem is more pronounced under language modeling with unbounded contexts. In this paper, we propose \textbf{L}inear \textbf{A}ttention \textbf{V}ia \textbf{O}rthogonal memory~(\shortname) to address these limitations, achieving strong performance while maintaining linear complexity. \shortname employs orthogonal decomposition to compress a context into a fixed-size orthogonal memory while effectively minimizing redundancy within the context. Given that orthogonal memory compresses global information, we further dissect the context to amplify fine-grained local information. Additionally, we embed the relative position encoding into \shortname to improve the extrapolation ability. Experimental results show that \shortname greatly improves the efficiency of the causal language model with the best extrapolation performance and outperforms other efficient baselines. Further, we endeavor to employ \shortname for unbounded language modeling and successfully scale the context length to 128K.

Related papers

• Scaling Linear Attention with Sparse State Expansion [58.161410995744596]
  Transformer architecture struggles with long-context scenarios due to quadratic computation and linear memory growth.<n>We introduce a row-sparse update formulation for linear attention by conceptualizing state updating as information classification.<n>Second, we present Sparse State Expansion (SSE) within the sparse framework, which expands the contextual state into multiple partitions.
  arXiv  Detail & Related papers  (2025-07-22T13:27:31Z)
• Curse of High Dimensionality Issue in Transformer for Long-context Modeling [31.257769500741006]
  We propose textitDynamic Group Attention (DGA) to reduce redundancy by aggregating less important tokens during attention computation.<n>Our results show that our DGA significantly reduces computational costs while maintaining competitive performance.
  arXiv  Detail & Related papers  (2025-05-28T08:34:46Z)
• Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models [49.84163262868945]
  Large language models have shown remarkable performance across a wide range of language tasks, owing to their exceptional capabilities in context modeling. The most commonly used method of context modeling is full self-attention, as seen in standard decoder-only Transformers. We propose parallel context encoding, which splits the context into sub-pieces and encodes them parallelly.
  arXiv  Detail & Related papers  (2024-12-21T09:04:51Z)
• DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization [61.492590008258986]
  Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. We propose DRPruning, which incorporates distributionally robust optimization to restore balanced performance across domains.
  arXiv  Detail & Related papers  (2024-11-21T12:02:39Z)
• Taipan: Efficient and Expressive State Space Language Models with Selective Attention [100.16383527459429]
  Long-context language modeling is a significant challenge in Natural Language Processing (NLP) Recent State Space Models (SSMs) such as Mamba offer alternatives with constant memory usage, but they underperform in tasks requiring extensive in-context retrieval. We introduce Taipan, a novel hybrid architecture that combines Mamba-2 with Selective Attention Layers (SALs) Our experiments demonstrate Taipan's superior performance across various scales and tasks, offering a promising solution for efficient long-context language modeling.
  arXiv  Detail & Related papers  (2024-10-24T09:25:37Z)
• CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling [52.404072802235234]
  We introduce Chunked Instruction-aware State Eviction (CItruS), a novel modeling technique that integrates the attention preferences useful for a downstream task into the eviction process of hidden states. Our training-free method exhibits superior performance on long sequence comprehension and retrieval tasks over several strong baselines under the same memory budget.
  arXiv  Detail & Related papers  (2024-06-17T18:34:58Z)
• Lean Attention: Hardware-Aware Scalable Attention Mechanism for the Decode-Phase of Transformers [4.674454841332859]
  Transformer-based models have emerged as one of the most widely used architectures for natural language processing. These huge models are memory hungry and incur significant inference latency even on cutting edge AI-accelerators. We propose LeanAttention, a scalable technique of computing self-attention for the token-generation phase.
  arXiv  Detail & Related papers  (2024-05-17T00:52:39Z)
• SpaceByte: Towards Deleting Tokenization from Large Language Modeling [0.0]
  Tokenization is widely used in large language models because it significantly improves performance. We propose SpaceByte, a novel byte-level decoder architecture that closes the performance gap between byte-level and subword autoregressive language modeling.
  arXiv  Detail & Related papers  (2024-04-22T17:59:29Z)
• Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs [61.40047491337793]
  We present Hierarchical cOntext MERging (HOMER), a new training-free scheme designed to overcome the limitations of large language models. HomeR uses a divide-and-conquer algorithm, dividing long inputs into manageable chunks. A token reduction technique precedes each merging, ensuring memory usage efficiency.
  arXiv  Detail & Related papers  (2024-04-16T06:34:08Z)
• Simple linear attention language models balance the recall-throughput tradeoff [60.06020449520365]
  We propose BASED, a simple architecture combining linear and sliding window attention. We train language models up to 1.3b parameters and show that BASED matches the strongest sub-quadratic models in perplexity and outperforms them on real-world recall-intensive tasks by 6.22 accuracy points.
  arXiv  Detail & Related papers  (2024-02-28T19:28:27Z)
• Vocabulary-level Memory Efficiency for Language Model Fine-tuning [36.1039389951318]
  We show that a significant proportion of the vocabulary remains unused during fine-tuning. We propose a simple yet effective approach that leverages this finding to minimize memory usage. Our approach does not impact downstream task performance, while allowing more efficient use of computational resources.
  arXiv  Detail & Related papers  (2023-09-15T19:00:00Z)
• Efficient Long Sequence Modeling via State Space Augmented Transformer [92.74707853711374]
  We propose SPADE, short for $underlinetextbfS$tate sunderlinetextbfP$ace. We augment a SSM into the bottom layer of SPADE, and we employ efficient local attention methods for the other layers. Experimental results on the Long Range Arena benchmark and language modeling tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2022-12-15T20:51:27Z)
• NFLAT: Non-Flat-Lattice Transformer for Chinese Named Entity Recognition [39.308634515653914]
  We advocate a novel lexical enhancement method, InterFormer, that effectively reduces the amount of computational and memory costs. Compared with FLAT, it reduces unnecessary attention calculations in "word-character" and "word-word" This reduces the memory usage by about 50% and can use more extensive lexicons or higher batches for network training.
  arXiv  Detail & Related papers  (2022-05-12T01:55:37Z)
• DCT-Former: Efficient Self-Attention with Discrete Cosine Transform [4.622165486890318]
  An intrinsic limitation of the Trasformer architectures arises from the computation of the dot-product attention. Our idea takes inspiration from the world of lossy data compression (such as the JPEG algorithm) to derive an approximation of the attention module. An extensive section of experiments shows that our method takes up less memory for the same performance, while also drastically reducing inference time.
  arXiv  Detail & Related papers  (2022-03-02T15:25:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.