{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/interpretable-geometric-deep-learning-via","title":"Interpretable Geometric Deep Learning via Learnable Randomness Injection","arxiv_id":"2210.16966","date":"2022-10-30","proceeding":null,"authors":["Siqi Miao","Yunan Luo","Mia Liu","Pan Li"],"abstract":"Point cloud data is ubiquitous in scientific fields. Recently, geometric deep learning (GDL) has been widely applied to solve prediction tasks with such data. However, GDL models are often complicated and hardly interpretable, which poses concerns to scientists who are to deploy these models in scientific analysis and experiments. This work proposes a general mechanism, learnable randomness injection (LRI), which allows building inherently interpretable models based on general GDL backbones. LRI-induced models, once trained, can detect the points in the point cloud data that carry information indicative of the prediction label. We also propose four datasets from real scientific applications that cover the domains of high-energy physics and biochemistry to evaluate the LRI mechanism. Compared with previous post-hoc interpretation methods, the points detected by LRI align much better and stabler with the ground-truth patterns that have actual scientific meanings. LRI is grounded by the information bottleneck principle, and thus LRI-induced models are also more robust to distribution shifts between training and test scenarios. Our code and datasets are available at \\url{https://github.com/Graph-COM/LRI}.","url_abs":"https://arxiv.org/abs/2210.16966v2","url_pdf":"https://arxiv.org/pdf/2210.16966v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"interpretable-geometric-deep-learning-via","repo_url":"https://github.com/graph-com/lri","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"interpretable-geometric-deep-learning-via","repo_url":"https://github.com/Graph-COM/xgdl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.16966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16966"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/Graph-COM/LRI","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Graph-COM/xgdl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/graph-com/lri","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"unverified":10},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":12,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e0fcdd921ca4873a","entry":"negative_augmentation","repo":"Graph-COM/LRI","repo_kind":"official","path":"src/trainer.py","file_url":"https://github.com/Graph-COM/LRI/blob/HEAD/src/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e0fcdd921ca4873a"}},{"code_sha256_prefix":"bc66f19be57720e7","entry":"unsorted_segment_mean","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/backbones/egnn.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/backbones/egnn.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc66f19be57720e7"}},{"code_sha256_prefix":"dfdf6dc1a0720e57","entry":"unsorted_segment_sum","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/backbones/egnn.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/backbones/egnn.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dfdf6dc1a0720e57"}},{"code_sha256_prefix":"bbe79497da57f1ba","entry":"act_transform","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/get_data.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/get_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bbe79497da57f1ba"}},{"code_sha256_prefix":"f763641d67617951","entry":"eval_one_batch","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/trainer.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f763641d67617951"}},{"code_sha256_prefix":"e71db67381e7e824","entry":"get_avg_std_report","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/pipeline.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e71db67381e7e824"}},{"code_sha256_prefix":"d55adf463cf24712","entry":"relabel","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/baselines/new_method.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/baselines/new_method.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d55adf463cf24712"}},{"code_sha256_prefix":"9448a7da7f38667f","entry":"save_multi_result","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/pipeline.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/pipeline.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9448a7da7f38667f"}},{"code_sha256_prefix":"463450ca2539b19d","entry":"select_augmentation","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/trainer.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"463450ca2539b19d"}},{"code_sha256_prefix":"deb2712a258e8789","entry":"split_batch","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/baselines/new_method.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/baselines/new_method.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"deb2712a258e8789"}},{"code_sha256_prefix":"c8deaefc82d78a0e","entry":"syn_transform","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/get_data.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/get_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c8deaefc82d78a0e"}},{"code_sha256_prefix":"934d3718469c1253","entry":"tau_transform","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/get_data.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/get_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"934d3718469c1253"}},{"code_sha256_prefix":"1a9589e2bc8498a8","entry":"train_one_batch","repo":"Graph-COM/xgdl","repo_kind":"listed","path":"src/xgdl/trainer.py","file_url":"https://github.com/Graph-COM/xgdl/blob/HEAD/src/xgdl/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a9589e2bc8498a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}