{"url":"/method/dst","slug":"dst","name":"DST","full_name":"Dynamic Sparse Training","full_name_withheld":false,"description_markdown":"Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","paper":"/paper/scalable-training-of-artificial-neural","first_author":"Decebal Constantin Mocanu","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/scalable-training-of-artificial-neural"},"source":{"url":"http://arxiv.org/abs/1707.04780v2","title":"Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Model Compression","url":"/methods/category/model-compression","pwc_aliases":[]}],"n_papers_tagged":205,"archive_num_papers":205,"papers_newest_first":[{"paper":null,"title":"Beyond Single-User Dialogue: Assessing Multi-User Dialogue State Tracking Capabilities of Large Language Models","date":"2025-06-12","arxiv_id":"2506.10504","n_code_links":0,"syntology":null},{"paper":null,"title":"Factors affecting the in-context learning abilities of LLMs for dialogue state tracking","date":"2025-06-10","arxiv_id":"2506.08753","n_code_links":0,"syntology":null},{"paper":null,"title":"Discovering Governing Equations of Geomagnetic Storm Dynamics with Symbolic Regression","date":"2025-04-25","arxiv_id":"2504.18461","n_code_links":0,"syntology":null},{"paper":null,"title":"Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs","date":"2025-03-11","arxiv_id":"2503.08857","n_code_links":0,"syntology":null},{"paper":null,"title":"Brain-inspired sparse training enables Transformers and LLMs to perform as fully connected","date":"2025-01-31","arxiv_id":"2501.19107","n_code_links":0,"syntology":null},{"paper":"/paper/towards-preventing-overreliance-on-task","title":"Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling","date":"2025-01-17","arxiv_id":"2501.10316","n_code_links":1,"syntology":null},{"paper":null,"title":"Prediction of Geoeffective CMEs Using SOHO Images and Deep Learning","date":"2025-01-02","arxiv_id":"2501.01011","n_code_links":0,"syntology":null},{"paper":null,"title":"Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"Intent-driven In-context Learning for Few-shot Dialogue State Tracking","date":"2024-12-04","arxiv_id":"2412.03270","n_code_links":0,"syntology":null},{"paper":null,"title":"Sparser Training for On-Device Recommendation Systems","date":"2024-11-19","arxiv_id":"2411.12205","n_code_links":0,"syntology":null},{"paper":"/paper/navigating-extremes-dynamic-sparsity-in-large","title":"Navigating Extremes: Dynamic Sparsity in Large Output Space","date":"2024-11-05","arxiv_id":"2411.03171","n_code_links":1,"syntology":{"ran":0,"of":6,"unverified":6,"pointer_only":6}},{"paper":"/paper/beyond-ontology-in-dialogue-state-tracking","title":"Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot","date":"2024-10-30","arxiv_id":"2410.22767","n_code_links":1,"syntology":null},{"paper":null,"title":"Reliability Assessment of Information Sources Based on Random Permutation Set","date":"2024-10-30","arxiv_id":"2410.22772","n_code_links":0,"syntology":null},{"paper":null,"title":"Tracing Human Stress from Physiological Signals using UWB Radar","date":"2024-10-14","arxiv_id":"2410.10155","n_code_links":0,"syntology":null},{"paper":null,"title":"Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training","date":"2024-09-28","arxiv_id":"2409.19391","n_code_links":0,"syntology":null},{"paper":"/paper/a-zero-shot-open-vocabulary-pipeline-for","title":"A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding","date":"2024-09-24","arxiv_id":"2409.15861","n_code_links":1,"syntology":null},{"paper":"/paper/confidence-estimation-for-llm-based-dialogue","title":"Confidence Estimation for LLM-Based Dialogue State Tracking","date":"2024-09-15","arxiv_id":"2409.09629","n_code_links":1,"syntology":{"ran":10,"of":12,"unverified":2,"pointer_only":12}},{"paper":null,"title":"Keyword-Aware ASR Error Augmentation for Robust Dialogue State Tracking","date":"2024-09-10","arxiv_id":"2409.06263","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-learning-and-computing-over","title":"Hierarchical Learning and Computing over Space-Ground Integrated Networks","date":"2024-08-26","arxiv_id":"2408.14116","n_code_links":1,"syntology":null},{"paper":null,"title":"Imprecise Belief Fusion Facing a DST benchmark problem","date":"2024-08-16","arxiv_id":"2408.08928","n_code_links":0,"syntology":null},{"paper":"/paper/unveiling-the-power-of-sparse-neural-networks","title":"Unveiling the Power of Sparse Neural Networks for Feature Selection","date":"2024-08-08","arxiv_id":"2408.04583","n_code_links":1,"syntology":null},{"paper":"/paper/2407-21633","title":"Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation","date":"2024-07-31","arxiv_id":"2407.21633","n_code_links":1,"syntology":{"ran":7,"of":10,"unverified":3,"pointer_only":10}},{"paper":null,"title":"TriQXNet: Forecasting Dst Index from Solar Wind Data Using an Interpretable Parallel Classical-Quantum Framework with Uncertainty Quantification","date":"2024-07-09","arxiv_id":"2407.06658","n_code_links":0,"syntology":null},{"paper":null,"title":"Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue","date":"2024-06-20","arxiv_id":"2406.14457","n_code_links":0,"syntology":null},{"paper":"/paper/a-two-dimensional-zero-shot-dialogue-state","title":"A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4","date":"2024-06-17","arxiv_id":"2406.11651","n_code_links":1,"syntology":null},{"paper":"/paper/decoder-only-streaming-transformer-for","title":"Decoder-only Streaming Transformer for Simultaneous Translation","date":"2024-06-06","arxiv_id":"2406.03878","n_code_links":1,"syntology":{"ran":1,"of":2,"unverified":1,"pointer_only":0}},{"paper":null,"title":"Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents","date":"2024-05-28","arxiv_id":"2405.17840","n_code_links":0,"syntology":null},{"paper":null,"title":"Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Tracking","date":"2024-05-21","arxiv_id":"2405.12468","n_code_links":0,"syntology":null},{"paper":null,"title":"A Versatile Framework for Analyzing Galaxy Image Data by Implanting Human-in-the-loop on a Large Vision Model","date":"2024-05-17","arxiv_id":"2405.10890","n_code_links":0,"syntology":null},{"paper":null,"title":"Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation","date":"2024-05-17","arxiv_id":"2405.13037","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/dialogue-state-tracking","name":"Dialogue State Tracking","papers":129},{"task":"/task/task-oriented-dialogue-systems","name":"Task-Oriented Dialogue Systems","papers":32},{"task":"/task/multi-domain-dialogue-state-tracking","name":"Multi-domain Dialogue State Tracking","papers":24},{"task":null,"name":"dialog state tracking","papers":20},{"task":"/task/language-modelling","name":"Language Modelling","papers":18},{"task":"/task/language-modeling","name":"Language Modeling","papers":16},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":15},{"task":"/task/decoder","name":"Decoder","papers":12},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":9},{"task":"/task/question-answering","name":"Question Answering","papers":9},{"task":"/task/slot-filling","name":"Slot Filling","papers":9},{"task":"/task/slot-filling-1","name":"slot-filling","papers":9},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":8},{"task":"/task/reading-comprehension","name":"Reading Comprehension","papers":7},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":6},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":6},{"task":"/task/response-generation","name":"Response Generation","papers":6},{"task":"/task/diversity","name":"Diversity","papers":5},{"task":"/task/management","name":"Management","papers":5},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":5}],"tasks_shown":20,"n_tasks":143,"usage_by_year":[{"year":"2017","papers":3},{"year":"2018","papers":8},{"year":"2019","papers":15},{"year":"2020","papers":32},{"year":"2021","papers":38},{"year":"2022","papers":34},{"year":"2023","papers":37},{"year":"2024","papers":30},{"year":"2025","papers":8}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dst"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}