Gyeong-Moon Park, Jun-Yeong Moon, Jung Uk
We lifted 9 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| KHU-AGI/HMDC | canonical | 6 of 9 |
| Function | Status | Where it lives |
|---|---|---|
| act_layer | Ran | KHU-AGI/HMDC/gcn_lib/torch_nn.py pointer only (licence: NONE) · get_code("9cb7add8f210b472") |
| batched_index_select | Ran | KHU-AGI/HMDC/gcn_lib/torch_nn.py pointer only (licence: NONE) · get_code("996eec2334fe011e") |
| norm_layer | Ran | KHU-AGI/HMDC/gcn_lib/torch_nn.py pointer only (licence: NONE) · get_code("09e6ddb17c0adf28") |
| pairwise_distance | Ran | KHU-AGI/HMDC/gcn_lib/torch_edge.py pointer only (licence: NONE) · get_code("82aeae314890e7ed") |
| part_pairwise_distance | Ran | KHU-AGI/HMDC/gcn_lib/torch_edge.py pointer only (licence: NONE) · get_code("102d0e5b09e9b385") |
| xy_pairwise_distance | Ran | KHU-AGI/HMDC/gcn_lib/torch_edge.py pointer only (licence: NONE) · get_code("160401504e7d0dbb") |
| get_2d_relative_pos_embed | Not yet run | KHU-AGI/HMDC/gcn_lib/pos_embed.py pointer only (licence: NONE) · get_code("571021715428528c") |
| get_2d_sincos_pos_embed | Not yet run | KHU-AGI/HMDC/gcn_lib/pos_embed.py pointer only (licence: NONE) · get_code("3185afc3e87293ed") |
| get_2d_sincos_pos_embed_from_grid | Not yet run | KHU-AGI/HMDC/gcn_lib/pos_embed.py pointer only (licence: NONE) · get_code("f10004e059714d42") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The advancement of deep learning has coincided with the proliferation of both models and available data. The surge in dataset sizes and the subsequent surge in computational requirements have led to the development of the Dataset Condensation (DC). While prior studies have delved into generating synthetic images through methods like distribution alignment and training trajectory tracking for more efficient model training, a significant challenge arises when employing these condensed images practically. Notably, these condensed images tend to be specific to particular models, constraining their versatility and practicality. In response to this limitation, we introduce a novel method, Heterogeneous Model Dataset Condensation (HMDC), designed to produce universally applicable condensed images through cross-model interactions. To address the issues of gradient magnitude difference and semantic distance in models when utilizing heterogeneous models, we propose the Gradient Balance Module (GBM) and Mutual Distillation (MD) with the Spatial-Semantic Decomposition method. By balancing the contribution of each model and maintaining their semantic meaning closely, our approach overcomes the limitations associated with model-specific condensed images and enhances the broader utility. The source code is available in https://github.com/KHU-AGI/HMDC.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2409.14538")
get_code_for_paper("2409.14538")
have("2409.14538")
Connect an agent — have() is free.